© 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. 14336
    Prev
    Next
    INDEX
    Explanations

    businessman

    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
     Reſ
    -0.82
     businessman
    -0.79
     ſmall
    -0.78
     greateſt
    -0.77
     faſt
    -0.76
    Geplaatst
    -0.76
     purpoſe
    -0.76
     Inscrivez
    -0.75
     businessmen
    -0.75
     houſe
    -0.75
    POSITIVE LOGITS
    <bos>
    0.55
    '
    0.50
    __((
    0.50
     for
    0.48
    ContentAsync
    0.47
     if
    0.46
    Παραπομπές
    0.44
     en
    0.43
    "?
    0.42
    +#+
    0.41
    Activations Density 0.022%

    No Known Activations