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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2897
    Prev
    Next
    INDEX
    Explanations

    forms/logins/URLs/code

    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
    abetta
    -0.55
     aggi
    -0.50
    included
    -0.49
     дописавши
    -0.48
    redit
    -0.48
    entre
    -0.47
     kasarigan
    -0.46
     arbres
    -0.44
    initWith
    -0.44
    ohjel
    -0.43
    POSITIVE LOGITS
    writeHead
    0.65
    providedIn
    0.65
     into
    0.64
    StructEnd
    0.64
    melons
    0.63
    клопе
    0.63
    TextSpan
    0.59
    InSection
    0.59
     {}));
    0.58
    istic
    0.57
    Activations Density 0.038%

    No Known Activations