© 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. 5-CLT-HP
    7. 95207
    Prev
    Next
    INDEX
    Explanations

    organizations

    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
    ValueStyle
    -0.66
    DeleteBehavior
    -0.58
    withIdentifier
    -0.50
    titutions
    -0.48
     survivor
    -0.47
    urlopen
    -0.47
     aDecoder
    -0.46
    日閲覧
    -0.45
    kson
    -0.45
    complexContent
    -0.43
    POSITIVE LOGITS
     for
    0.72
    <bos>
    0.63
     of
    0.60
    contentLoaded
    0.55
    findpost
    0.55
     للمعارف
    0.53
     ivelany
    0.52
     विश्वसनीयता
    0.52
     jScrollPane
    0.50
     soutient
    0.50
    Activations Density 0.002%

    No Known Activations