© 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. 4697
    Prev
    Next
    INDEX
    Explanations

    loose

    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
    󠁿
    -0.50
    Erstellt
    -0.48
    Просто
    -0.48
    Andi
    -0.47
     Hera
    -0.47
     Andi
    -0.46
    CancelButton
    -0.45
     Cheney
    -0.45
    rdı
    -0.45
    +:+
    -0.44
    POSITIVE LOGITS
    mybatisplus
    0.79
    fill
    0.69
    leaf
    0.69
    jspx
    0.66
    providedIn
    0.65
     дописавши
    0.63
    fillType
    0.63
    parts
    0.59
     fill
    0.57
    styleUrls
    0.57
    Activations Density 0.002%

    No Known Activations