© 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. 92485
    Prev
    Next
    INDEX
    Explanations

    scientific and medical contexts

    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
    acea
    -0.50
    coroutines
    -0.48
    modb
    -0.47
    urances
    -0.46
     angekommen
    -0.43
    urement
    -0.43
    oplus
    -0.43
    coration
    -0.43
    SYNOPSIS
    -0.42
    imals
    -0.42
    POSITIVE LOGITS
    rungsseite
    0.66
    SourceChecksum
    0.64
     snippetHide
    0.61
     Италијани
    0.59
    XtraReports
    0.58
     ModelExpression
    0.58
     photographers
    0.57
    LogFactory
    0.57
    IsMutable
    0.56
    Personendaten
    0.56
    Activations Density 0.008%

    No Known Activations