© 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. 1084
    Prev
    Next
    INDEX
    Explanations

    feeling

    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
     feeling
    -1.87
    feeling
    -1.53
     Feeling
    -1.41
    Feeling
    -1.30
     sensazione
    -1.07
     smelling
    -0.96
     Feelings
    -0.93
     feelings
    -0.91
     gevoel
    -0.91
     sentimiento
    -0.91
    POSITIVE LOGITS
    ing
    0.51
    évaluateur
    0.50
    astéro
    0.49
    ткий
    0.47
    er
    0.46
     status
    0.46
    ING
    0.45
     Cha
    0.43
    ه
    0.42
    mpotent
    0.41
    Activations Density 1.597%

    No Known Activations