© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46277
    Prev
    Next
    INDEX
    Explanations

    cull

    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
     PRES
    -0.59
    BRACKET
    -0.58
    LETE
    -0.57
     Kale
    -0.55
     Pres
    -0.55
    zam
    -0.54
    RTLR
    -0.52
    expliquer
    -0.52
     Repe
    -0.52
    Kale
    -0.52
    POSITIVE LOGITS
    ScopeManager
    0.68
     Roskov
    0.51
     cherchés
    0.50
    StructEnd
    0.49
    服
    0.46
    GenerationType
    0.44
    gery
    0.44
    ритори
    0.44
    koľ
    0.43
     propOrder
    0.43
    Activations Density 0.060%

    No Known Activations