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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14278
    Prev
    Next
    INDEX
    Explanations

    terms related to poisoning or toxic substances

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    479
    +0.15
    0.6%
    1763
    +0.14
    0.5%
    889
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1763
    +0.15
    0.03
    468
    +0.14
    0.02
    479
    +0.14
    0.02
    Negative Logits
    OGND
    -0.48
    Präsident
    -0.44
    ężczy
    -0.43
    éu
    -0.43
    tagHelperRunner
    -0.42
     Capit
    -0.41
    Trama
    -0.41
    Anders
    -0.41
    Jeb
    -0.41
    acp
    -0.41
    POSITIVE LOGITS
     poisoning
    1.04
     poison
    1.03
     toxic
    0.99
     poisoned
    0.96
    poison
    0.95
     Poison
    0.93
     toxin
    0.90
     poisonous
    0.90
    Poison
    0.89
     toxins
    0.88
    Activations Density 0.099%

    No Known Activations