© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42164
    Prev
    Next
    INDEX
    Explanations

    aggression

    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
     anger
    -1.10
     aggression
    -0.98
     angry
    -0.84
     Aggression
    -0.82
     fury
    -0.82
     Anger
    -0.75
     resentment
    -0.74
     rage
    -0.73
     Angry
    -0.72
    Angry
    -0.69
    POSITIVE LOGITS
     thermique
    0.73
     jorden
    0.68
    endency
    0.64
    StructEnd
    0.64
    AndEndTag
    0.63
    Personensuche
    0.61
     vôtre
    0.61
     itſelf
    0.61
     nemlig
    0.60
     carreaux
    0.60
    Activations Density 1.459%

    No Known Activations