© 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. 20-CLT-HP
    7. 72468
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act-logits · 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
     BrowserModule
    -0.69
    OGND
    -0.68
     propOrder
    -0.67
    Jegyzetek
    -0.63
     незавершена
    -0.63
    PrototypeOf
    -0.62
    IsContent
    -0.61
    Brainz
    -0.60
    riwal
    -0.57
    IGraphics
    -0.57
    POSITIVE LOGITS
     pamamagitan
    0.50
    )$}
    0.45
    }])
    0.44
     bestä
    0.43
    []}
    0.42
     aguacate
    0.42
    pues
    0.41
     !!}
    0.41
     frumo
    0.41
     rueda
    0.41
    Activations Density 0.000%

    No Known Activations