© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95239
    Prev
    Next
    INDEX
    Explanations

    sample

    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
     of
    -0.79
     samples
    -0.78
    ########.
    -0.77
    InjectAttribute
    -0.76
    $_['
    -0.75
     kaarangay
    -0.75
    DeleteBehavior
    -0.75
     nakalista
    -0.74
    OfWork
    -0.72
     SAMPLES
    -0.71
    POSITIVE LOGITS
    ,
    0.47
    .
    0.47
    -
    0.42
     itong
    0.42
    ↵
    0.41
    телна
    0.41
     '
    0.40
    "
    0.39
     emot
    0.39
     I
    0.39
    Activations Density 0.124%

    No Known Activations