© 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. 45296
    Prev
    Next
    INDEX
    Explanations

    academic documents

    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
    iformis
    -1.48
    minster
    -0.88
    vice
    -0.86
     îna
    -0.64
    Portale
    -0.63
    Portail
    -0.62
     vice
    -0.59
    formis
    -0.59
     définiti
    -0.59
    AndroidJUnit
    -0.57
    POSITIVE LOGITS
    IndentedString
    0.63
     celib
    0.54
    GOTREF
    0.53
    UnknownFieldSet
    0.50
     يتيمه
    0.46
    География
    0.45
     moderate
    0.44
    ANTLR
    0.44
     drops
    0.44
    }();
    0.44
    Activations Density 0.021%

    No Known Activations