© 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. 4-CLT-HP
    7. 3284
    Prev
    Next
    INDEX
    Explanations

    emotions

    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
     defStyleAttr
    -0.60
     Bioaccumulative
    -0.57
    autres
    -0.56
     sum
    -0.54
    BETWEEN
    -0.54
    jsxFileName
    -0.54
     daher
    -0.53
    最快更新
    -0.52
     THOUGH
    -0.52
    сюда
    -0.50
    POSITIVE LOGITS
     that
    0.66
     how
    0.66
    GEBURTSDATUM
    0.55
    <bos>
    0.52
    ArgsConstructor
    0.50
    viewDidLoad
    0.49
    StreetMap
    0.48
    ⓧ
    0.48
    ніципа
    0.48
     what
    0.47
    Activations Density 0.005%

    No Known Activations