© 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. 38762
    Prev
    Next
    INDEX
    Explanations

    want

    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
     want
    -1.44
    want
    -1.27
     wanted
    -1.26
     wants
    -1.23
     Want
    -1.21
     wanting
    -1.12
    wanted
    -1.10
    Want
    -1.07
     Wants
    -1.02
    wants
    -1.00
    POSITIVE LOGITS
     to
    1.10
    <bos>
    0.77
     us
    0.69
     China
    0.54
     me
    0.53
    ances
    0.53
     препратки
    0.53
    ing
    0.50
     विश्वसनीयता
    0.50
    QMetaType
    0.50
    Activations Density 0.088%

    No Known Activations