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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4591
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.65
    ;
    -0.57
    /
    -0.56
    <eos>
    -0.55
    ,
    -0.52
    ...
    -0.52
    .
    -0.51
    ....
    -0.49
    …
    -0.49
    ↵
    -0.48
    POSITIVE LOGITS
     itſelf
    1.67
     myſelf
    1.61
     raiſ
    1.52
     purpoſe
    1.52
     pleaſure
    1.52
    ſelf
    1.50
     themſelves
    1.48
     Efq
    1.46
     Jefus
    1.45
     houſe
    1.44
    Activations Density 2.115%

    No Known Activations