© 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. 4414
    Prev
    Next
    INDEX
    Explanations

    also

    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
     pinulongan
    -0.85
    IndentedString
    -0.74
    WebVitals
    -0.68
    adə
    -0.68
     nahilalakip
    -0.66
     बजाय
    -0.65
     يتيمه
    -0.63
     preferring
    -0.61
    Kanpo
    -0.61
    oredCriteria
    -0.60
    POSITIVE LOGITS
    <bos>
    0.55
    ):=\
    0.54
    ):=
    0.49
    */].
    0.48
    也
    0.47
    stopPropagation
    0.45
    VIAF
    0.45
     pico
    0.44
     also
    0.43
     engag
    0.43
    Activations Density 0.006%

    No Known Activations