© 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. 91769
    Prev
    Next
    INDEX
    Explanations

    seen/shown

    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
    LookAnd
    -0.83
    ArgsConstructor
    -0.77
    enapa
    -0.73
     AssemblyTitle
    -0.68
     natale
    -0.66
    wapV
    -0.66
    GenerationType
    -0.66
     Efq
    -0.66
     læng
    -0.65
    Brainz
    -0.65
    POSITIVE LOGITS
     on
    0.45
     jsPsych
    0.39
     in
    0.39
    ochim
    0.39
    BrowserModule
    0.38
    rend
    0.37
    nics
    0.36
    shank
    0.35
     another
    0.35
    pj
    0.35
    Activations Density 0.004%

    No Known Activations