© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38906
    Prev
    Next
    INDEX
    Explanations

    Programming, pronouns, "super" keyword

    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
     identity
    -0.99
     identities
    -0.96
     Identity
    -0.86
     identité
    -0.80
     Identi
    -0.79
     identidad
    -0.74
     IDENTITY
    -0.72
     Identities
    -0.70
    identity
    -0.69
     Identität
    -0.64
    POSITIVE LOGITS
     invokingState
    0.57
    featureID
    0.51
    Geplaatst
    0.51
    maketitle
    0.50
    MigrationBuilder
    0.49
     Надо
    0.48
    iprot
    0.48
    Demografie
    0.48
     getopt
    0.47
     насеље
    0.46
    Activations Density 0.128%

    No Known Activations