© 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. 1-CLT-HP
    7. 12125
    Prev
    Next
    INDEX
    Explanations

    map

    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
     map
    -1.36
     Map
    -1.22
     maps
    -1.16
    Map
    -1.11
    map
    -1.09
     Maps
    -1.02
     Mapping
    -1.00
     mapping
    -0.96
    maps
    -0.95
    MAP
    -0.91
    POSITIVE LOGITS
     Efq
    0.71
    Autoritní
    0.68
    Tikang
    0.68
     يتيمه
    0.68
     дописавши
    0.66
     فريبيس
    0.66
     pageContext
    0.65
     Monfieur
    0.63
     oprot
    0.63
     createSlice
    0.60
    Activations Density 0.009%

    No Known Activations