© 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. 94330
    Prev
    Next
    INDEX
    Explanations

    real

    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
     real
    -1.14
    real
    -0.73
     réel
    -0.61
     реаль
    -0.61
     réelle
    -0.57
    Real
    -0.55
     REAL
    -0.55
     actual
    -0.52
     vrai
    -0.51
     Real
    -0.50
    POSITIVE LOGITS
    <bos>
    0.78
     Bolshe
    0.78
     lordship
    0.78
     Athenian
    0.76
     purpoſe
    0.74
    isations
    0.73
     sceptre
    0.73
    MigrationBuilder
    0.72
     Athenians
    0.70
     Montmartre
    0.69
    Activations Density 0.025%

    No Known Activations