Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97831
    Prev
    Next
    INDEX
    Explanations

    anger or negativity

    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
    ing
    -0.80
     anger
    -0.72
     inactivity
    -0.71
    ſelf
    -0.71
     colère
    -0.68
     Angry
    -0.68
    theless
    -0.68
     ſmall
    -0.66
     angry
    -0.65
     powerless
    -0.65
    POSITIVE LOGITS
    таратура
    0.53
     bet
    0.50
     cu
    0.50
    <blockquote>
    0.48
    ForResult
    0.48
    PyExc
    0.47
     contra
    0.46
    AssignableFrom
    0.45
    ooker
    0.45
    javadoc
    0.44
    Activations Density 0.485%

    No Known Activations