© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 752
    Prev
    Next
    INDEX
    Explanations

    sensory-related terms related to frost

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1271
    +0.08
    0.2%
    1994
    +0.07
    0.2%
    1328
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.06
    283
    +0.07
    0.02
    690
    +0.07
    0.05
    Negative Logits
     ideolog
    -0.71
     koste
    -0.69
     roh
    -0.69
     alko
    -0.68
     mene
    -0.66
     mies
    -0.65
     vaid
    -0.62
     maksi
    -0.62
     elek
    -0.62
     lemp
    -0.62
    POSITIVE LOGITS
     Frost
    1.29
    Frost
    1.25
     vété
    1.23
     jelly
    1.18
     Docteur
    1.17
     milf
    1.16
     frost
    1.14
     véhic
    1.12
     carrefour
    1.12
     Jelly
    1.11
    Activations Density 0.330%

    No Known Activations