© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 467
    Prev
    Next
    INDEX
    Explanations

    names starting with "elle"

    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
    462
    +0.07
    0.2%
    489
    +0.07
    0.2%
    755
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.07
    0.06
    283
    +0.07
    0.01
    184
    +0.07
    0.02
    Negative Logits
     Pièces
    -0.81
     Portail
    -0.78
     Mémoires
    -0.75
     Mémoire
    -0.73
     Voulez
    -0.70
     Autres
    -0.68
     Autre
    -0.67
     Église
    -0.65
     Prés
    -0.64
     Violon
    -0.64
    POSITIVE LOGITS
     maer
    1.13
    elle
    1.04
     flare
    1.00
     flair
    1.00
     aen
    0.92
     gaily
    0.91
     practition
    0.90
     exacer
    0.89
     puff
    0.87
     unve
    0.87
    Activations Density 0.343%

    No Known Activations