© 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. 45115
    Prev
    Next
    INDEX
    Explanations

    words & variations

    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
     words
    -0.69
    words
    -0.65
    Words
    -0.64
     doubtnut
    -0.63
     goddesses
    -0.63
    paravant
    -0.63
     bershka
    -0.60
     myſelf
    -0.60
     photolibrary
    -0.60
     itſelf
    -0.59
    POSITIVE LOGITS
    GEBURTSDATUM
    0.69
    thâu
    0.64
     of
    0.53
     chi̍t
    0.53
    invokeLater
    0.52
     useSelector
    0.51
    UrlResolution
    0.51
    BagConstraints
    0.50
    TagMode
    0.50
    InjectAttribute
    0.50
    Activations Density 0.060%

    No Known Activations