© 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. 1-CLT-HP
    7. 15073
    Prev
    Next
    INDEX
    Explanations

    of

    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
    brigens
    -0.53
    endphp
    -0.52
     œufs
    -0.51
     χρήση
    -0.51
    onOptions
    -0.50
     useCallback
    -0.49
    ścioła
    -0.48
     Poles
    -0.47
    RetentionPolicy
    -0.47
     fixé
    -0.47
    POSITIVE LOGITS
     InputDecoration
    0.59
     definitions
    0.57
     CWE
    0.56
     calloc
    0.51
     volume
    0.51
     classification
    0.50
    éphane
    0.50
    ComponentModel
    0.50
     measurements
    0.50
     branch
    0.49
    Activations Density 0.014%

    No Known Activations