© 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. 5086
    Prev
    Next
    INDEX
    Explanations

    to

    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
     parlando
    -0.63
     reaping
    -0.59
     milking
    -0.59
    protoc
    -0.58
     becauſe
    -0.56
     touching
    -0.56
    OGND
    -0.56
     Efq
    -0.56
    gwt
    -0.55
     touring
    -0.54
    POSITIVE LOGITS
     survive
    0.69
     function
    0.66
     be
    0.60
     stay
    0.57
    function
    0.56
     Function
    0.53
     survie
    0.52
    Function
    0.51
    fromString
    0.51
     funcione
    0.50
    Activations Density 0.003%

    No Known Activations