© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4908
    Prev
    Next
    INDEX
    Explanations

    bot

    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
    tima
    -0.45
    erea
    -0.43
    raiser
    -0.38
     int
    -0.36
     male
    -0.36
    igne
    -0.35
    fum
    -0.35
    int
    -0.35
     super
    -0.35
     sus
    -0.34
    POSITIVE LOGITS
     الحره
    1.09
    ⓧ
    1.02
    IntoConstraints
    0.99
     snippetHide
    0.96
    BeginContext
    0.90
     <=",
    0.90
    SourceChecksum
    0.87
     ModelExpression
    0.87
    WaitGroup
    0.87
    tagHelperRunner
    0.83
    Activations Density 0.417%

    No Known Activations