© 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. 97680
    Prev
    Next
    INDEX
    Explanations

    xmlns

    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
    argout
    -0.54
     har
    -0.51
     Hang
    -0.51
    umą
    -0.50
     جان
    -0.49
     Gira
    -0.48
     Snap
    -0.48
     reports
    -0.47
    coste
    -0.47
     final
    -0.47
    POSITIVE LOGITS
     nakalista
    0.86
     JpaRepository
    0.82
     amitié
    0.79
     démocratie
    0.75
     fourrure
    0.73
     colère
    0.71
     bershka
    0.69
     Efq
    0.69
    يكب
    0.69
     متعلقه
    0.68
    Activations Density 1.819%

    No Known Activations