© 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. 1-CLT-HP
    4. 15492
    Prev
    Next
    INDEX
    Explanations

    famous

    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
    BagConstraints
    -0.57
    salsa
    -0.55
    Демографія
    -0.55
     Italijanski
    -0.55
    колай
    -0.54
    الحياه
    -0.53
    BindView
    -0.53
     ResponseEntity
    -0.52
     كمان
    -0.51
    ^(@)
    -0.51
    POSITIVE LOGITS
    mishes
    0.47
    tellation
    0.46
     colorir
    0.45
     avanti
    0.44
     дописавши
    0.43
    ItemClick
    0.43
     jLabel
    0.42
     Proprietary
    0.42
    monials
    0.41
    Зноскі
    0.41
    Activations Density 0.002%

    No Known Activations