© 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. 4-CLT-HP
    7. 1008
    Prev
    Next
    INDEX
    Explanations

    personal narratives

    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
     us
    -0.78
     me
    -0.65
    })`
    -0.58
    fhir
    -0.57
     stanovnika
    -0.56
    ']):
    -0.56
    ActionMode
    -0.55
    ')):
    -0.55
    SourceChecksum
    -0.52
    us
    -0.52
    POSITIVE LOGITS
     autorytatywna
    0.72
    IGraphics
    0.57
    KommentareTeilen
    0.57
    toThrow
    0.54
    jsonwebtoken
    0.54
    Personendaten
    0.53
     anfangen
    0.53
     back
    0.52
     suggesting
    0.50
    ⓘ
    0.48
    Activations Density 0.003%

    No Known Activations