© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3714
    Prev
    Next
    INDEX
    Explanations

    to

    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
    StructEnd
    -0.58
    initializeApp
    -0.57
    CompleteListener
    -0.54
    __*/
    -0.54
    ="#"><
    -0.50
     Exacts
    -0.50
     kaynağından
    -0.47
     ngân
    -0.46
     redistribute
    -0.45
    gorov
    -0.45
    POSITIVE LOGITS
     Италијани
    0.55
     Italijanski
    0.55
    MigrationBuilder
    0.53
    licet
    0.53
    LOTTE
    0.52
     SafeMath
    0.50
    petto
    0.50
    äť
    0.50
     Efq
    0.49
    SuppressLint
    0.49
    Activations Density 0.001%

    No Known Activations