© 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. 91373
    Prev
    Next
    INDEX
    Explanations

    that can

    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
    <eos>
    -0.49
     in
    -0.49
     later
    -0.47
    ,
    -0.46
     that
    -0.46
     as
    -0.44
     
    -0.44
     after
    -0.44
     when
    -0.43
     —
    -0.43
    POSITIVE LOGITS
     nahilalakip
    1.09
     nakalista
    1.09
     myſelf
    1.08
     Theſe
    1.05
     purpoſe
    1.02
     متعلقه
    1.02
     itſelf
    1.02
     whoſe
    0.99
     Wikimedijinoj
    0.98
     ſeveral
    0.97
    Activations Density 0.010%

    No Known Activations