© 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. 5-CLT-HP
    7. 5072
    Prev
    Next
    INDEX
    Explanations

    changes and current events

    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
     bagi
    -0.41
    XmlIgnore
    -0.40
     bronzo
    -0.40
    voorbeeld
    -0.39
    ud
    -0.39
     kepada
    -0.38
     animato
    -0.38
    ｀*)
    -0.37
    -
    -0.37
     f
    -0.36
    POSITIVE LOGITS
     $_"
    0.68
    хьтан
    0.67
    WireFormatLite
    0.62
     Administrativna
    0.61
     חיצוניים
    0.61
     незавершена
    0.60
    ORETICAL
    0.60
    IFORNIA
    0.59
     thinking
    0.59
    LayoutStyle
    0.59
    Activations Density 0.000%

    No Known Activations