© 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. 97640
    Prev
    Next
    INDEX
    Explanations

    completion or initiation

    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
     estekak
    -0.70
    iest
    -0.69
     nakalista
    -0.66
     متعلقه
    -0.65
     оригіналу
    -0.62
    rrggbb
    -0.60
     horaire
    -0.59
    ंदीखरीदारी
    -0.59
    Enders
    -0.58
    ists
    -0.57
    POSITIVE LOGITS
     the
    0.90
     our
    0.62
     some
    0.55
    writeFieldEnd
    0.55
     her
    0.52
     an
    0.51
    bitset
    0.50
     his
    0.50
     this
    0.48
     heavily
    0.47
    Activations Density 0.045%

    No Known Activations