© 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. 3352
    Prev
    Next
    INDEX
    Explanations

    priorities

    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
    IGraphics
    -0.64
     travaillons
    -0.64
    yelitis
    -0.60
    SourceChecksum
    -0.59
     الحره
    -0.57
    ❉
    -0.56
    HandlerContext
    -0.55
     juridiques
    -0.54
    numerusform
    -0.53
    lucene
    -0.53
    POSITIVE LOGITS
     protoimpl
    0.60
    Билгалдахарш
    0.59
    kloped
    0.58
     }}"></
    0.54
     movers
    0.54
     moving
    0.52
     "{}
    0.52
     managers
    0.51
     to
    0.51
    oredCriteria
    0.51
    Activations Density 0.002%

    No Known Activations