© 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. 0-CLT-HP
    7. 42435
    Prev
    Next
    INDEX
    Explanations

    {

    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
     to
    -0.53
     Nullable
    -0.52
    setTo
    -0.52
     educativas
    -0.49
     treatment
    -0.46
    rin
    -0.46
    <tr>
    -0.45
    letterSpacing
    -0.44
    odorant
    -0.43
     aéreas
    -0.43
    POSITIVE LOGITS
    RegressionTest
    0.84
     Roskov
    0.82
    Geplaatst
    0.82
    rungsseite
    0.80
    awtextra
    0.77
     createState
    0.74
    ConstraintMaker
    0.73
    LookAnd
    0.73
     indisponible
    0.71
    WireFormatLite
    0.70
    Activations Density 0.252%

    No Known Activations