© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94974
    Prev
    Next
    INDEX
    Explanations

    First

    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
    <bos>
    -0.62
    Diweddarwch
    -0.52
     bezeichneter
    -0.51
     виправивши
    -0.50
     démocr
    -0.48
     transfé
    -0.48
     supprim
    -0.47
    bentar
    -0.47
     destinées
    -0.47
     connues
    -0.47
    POSITIVE LOGITS
    +#+
    0.59
     thirds
    0.59
    flashdata
    0.57
    cians
    0.55
     createState
    0.55
    glVertex
    0.54
    ulose
    0.54
     Aene
    0.54
    RectangleBorder
    0.52
     Balik
    0.52
    Activations Density 0.022%

    No Known Activations