© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 94989
    Prev
    Next
    INDEX
    Explanations

    Hank/hankering

    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
     Hank
    -1.98
    Hank
    -1.74
    +#+#
    -1.06
     hank
    -1.05
    MigrationBuilder
    -1.04
    InvalidProtocol
    -1.01
    TabIndex
    -0.97
    hank
    -0.96
    ьаж
    -0.95
     unknownFields
    -0.92
    POSITIVE LOGITS
    ins
    0.57
    INS
    0.46
    omal
    0.43
    зора
    0.43
    拼
    0.42
    iew
    0.42
    isi
    0.42
    insp
    0.41
    Ins
    0.41
    INST
    0.40
    Activations Density 0.249%

    No Known Activations