© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94509
    Prev
    Next
    INDEX
    Explanations

    itself

    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
     itself
    -0.99
    itself
    -0.82
     himself
    -0.79
     Itself
    -0.78
     themselves
    -0.74
     herself
    -0.70
    himself
    -0.69
     Himself
    -0.68
    themselves
    -0.65
    herself
    -0.56
    POSITIVE LOGITS
    MigrationBuilder
    0.71
     lievito
    0.59
    styleType
    0.58
     NSCoder
    0.57
     morire
    0.57
     thermique
    0.57
    aspectRatio
    0.57
     navideña
    0.56
     imprimée
    0.56
    labus
    0.56
    Activations Density 0.015%

    No Known Activations