© 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. 72372
    Prev
    Next
    INDEX
    Explanations

    Scientific and technical contexts

    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
    tagHelperRunner
    -0.96
    AddTagHelper
    -0.87
    TypedDataSet
    -0.80
    +:+
    -0.71
    alamus
    -0.69
    servers
    -0.65
    mybatisplus
    -0.65
    NSNotification
    -0.64
    IContainer
    -0.64
    Gön
    -0.64
    POSITIVE LOGITS
     men
    0.65
     obispo
    0.42
     jur
    0.41
     homens
    0.39
     solare
    0.38
     души
    0.38
    cinta
    0.37
    ژ
    0.36
     nen
    0.35
     egent
    0.35
    Activations Density 0.000%

    No Known Activations