© 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. 14879
    Prev
    Next
    INDEX
    Explanations

    named entities

    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
    `{.
    -0.59
    pexpr
    -0.57
    createCanvas
    -0.57
    }_{+
    -0.54
    gatsby
    -0.54
     Mejía
    -0.54
    createStatement
    -0.54
    verwijspagina
    -0.53
    IndentedString
    -0.53
    AutoScale
    -0.53
    POSITIVE LOGITS
     Lovers
    0.46
     الحره
    0.46
     PROPERTY
    0.45
    Collective
    0.45
     DAMAGES
    0.44
     Devils
    0.44
     dalamnya
    0.43
     vapeur
    0.43
     sociétés
    0.42
     Sellers
    0.42
    Activations Density 0.027%

    No Known Activations