© 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. 95031
    Prev
    Next
    INDEX
    Explanations

    Broad, varying topics

    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
     upheaval
    -0.60
    GenerationType
    -0.57
     relâche
    -0.57
     تانيه
    -0.56
    FailureListener
    -0.56
    Initializable
    -0.56
    lementary
    -0.55
    expandindo
    -0.54
    citep
    -0.54
    RetentionPolicy
    -0.53
    POSITIVE LOGITS
    bell
    0.59
     CWE
    0.59
    bel
    0.58
    GraphicsUnit
    0.56
    AutoScaleMode
    0.55
    ticks
    0.52
     /\.(
    0.52
    parsedMessage
    0.52
    hyrchwyd
    0.51
    bro
    0.50
    Activations Density 0.154%

    No Known Activations