© 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. 5-CLT-HP
    7. 95219
    Prev
    Next
    INDEX
    Explanations

    correctness

    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
     Roskov
    -0.72
     dieux
    -0.58
     supérieures
    -0.57
     juridiques
    -0.56
     commerciaux
    -0.56
     météo
    -0.54
     supérieurs
    -0.54
     fédé
    -0.54
     direito
    -0.54
     genoux
    -0.53
    POSITIVE LOGITS
     OFDb
    0.59
    principalTable
    0.50
    IndentedString
    0.49
     {}".
    0.46
     nakalista
    0.46
    NOPQRST
    0.46
    וויק
    0.44
    VersionUID
    0.44
    arResult
    0.43
     ujednoznacz
    0.43
    Activations Density 0.001%

    No Known Activations