© 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. 92552
    Prev
    Next
    INDEX
    Explanations

    the

    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
     betweenstory
    -1.23
    SerializedSize
    -0.75
    AccessorTable
    -0.75
     propOrder
    -0.73
    __(/*!
    -0.71
    RetentionPolicy
    -0.67
    StateToProps
    -0.65
     disambiguazione
    -0.64
    IndentedString
    -0.63
     Theſe
    -0.62
    POSITIVE LOGITS
     crois
    0.56
    cshtml
    0.54
     as
    0.47
     closing
    0.44
     closure
    0.43
    closure
    0.41
    unicaciones
    0.41
    closing
    0.40
    viny
    0.40
     subsequent
    0.40
    Activations Density 0.002%

    No Known Activations