© 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. 92644
    Prev
    Next
    INDEX
    Explanations

    call

    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
     autorytatywna
    -0.79
     <=",
    -0.76
    Geplaatst
    -0.65
    principalTable
    -0.60
    новниш
    -0.60
    Abitanti
    -0.59
    WindowConstants
    -0.59
    elemField
    -0.58
     wireType
    -0.57
    Tikang
    -0.57
    POSITIVE LOGITS
     the
    0.69
    ietal
    0.60
     its
    0.58
    memoized
    0.55
    Portale
    0.52
     tölt
    0.51
     his
    0.49
    malla
    0.49
     ‘
    0.48
    сшта
    0.47
    Activations Density 0.005%

    No Known Activations