© 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. 91992
    Prev
    Next
    INDEX
    Explanations

    Document snippets

    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
     Permanent
    -0.40
     getAccount
    -0.40
    <eos>
    -0.40
    Kon
    -0.40
    ↵↵
    -0.40
    inen
    -0.40
    Permanent
    -0.40
     }
    -0.39
    ว
    -0.39
    ↵↵↵
    -0.39
    POSITIVE LOGITS
     فريبيس
    1.02
    ftagPool
    1.00
    GEBURTSDATUM
    0.98
     désolés
    0.87
    новниш
    0.86
     BoxFit
    0.85
    MethodManager
    0.85
     BorderRadius
    0.82
     ujednoznacz
    0.82
     Roskov
    0.82
    Activations Density 1.705%

    No Known Activations