© 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. 1-CLT-HP
    7. 15321
    Prev
    Next
    INDEX
    Explanations

    of

    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
    as
    -0.49
    wnie
    -0.47
    ilig
    -0.46
    se
    -0.45
    ‗
    -0.43
    '
    -0.43
    <eos>
    -0.43
     "
    -0.42
    raco
    -0.42
    مند
    -0.42
    POSITIVE LOGITS
    StoryboardSegue
    0.73
    MENAFN
    0.73
     BoxFit
    0.71
     parenthood
    0.71
     lordship
    0.69
     hope
    0.68
     Administrativna
    0.68
    OrNil
    0.68
     itſelf
    0.68
    AddTagHelper
    0.67
    Activations Density 0.057%

    No Known Activations