© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 95006
    Prev
    Next
    INDEX
    Explanations

    immutable

    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
    stdc
    -0.96
    StoryboardSegue
    -0.93
    Personendaten
    -0.93
     समीक्षाओं
    -0.93
     estekak
    -0.92
    abestanden
    -0.92
    tagHelperRunner
    -0.91
     المعيارى
    -0.89
    GraphicsUnit
    -0.89
     ExecuteAsync
    -0.88
    POSITIVE LOGITS
     matter
    0.50
     truth
    0.49
     strategic
    0.45
     dri
    0.44
     situation
    0.44
     character
    0.43
     circumstances
    0.42
     guest
    0.42
     small
    0.42
     second
    0.41
    Activations Density 0.090%

    No Known Activations