© 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. 14887
    Prev
    Next
    INDEX
    Explanations

    sure

    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
     beginnetje
    -0.78
     Roskov
    -0.73
     Majefty
    -0.62
     leçon
    -0.62
     scattata
    -0.60
     mariée
    -0.59
     Jefus
    -0.58
    Lähteet
    -0.58
     miſ
    -0.58
     necessaria
    -0.57
    POSITIVE LOGITS
    VertexAttrib
    0.59
     I
    0.58
    ChildScrollView
    0.54
    culable
    0.48
    География
    0.47
     it
    0.46
    versible
    0.46
     XL
    0.45
     its
    0.45
    __(/*!
    0.45
    Activations Density 0.042%

    No Known Activations