© 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. 2213
    Prev
    Next
    INDEX
    Explanations

    and

    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
     to
    -0.68
     opérateur
    -0.49
    Cie
    -0.48
    indd
    -0.47
     ca
    -0.46
     nyelven
    -0.45
    ownerId
    -0.45
    rijving
    -0.44
    agonia
    -0.44
     It
    -0.43
    POSITIVE LOGITS
     which
    1.29
    which
    1.12
    Which
    0.98
     WHICH
    0.89
     whose
    0.86
     Which
    0.85
     cuyo
    0.84
    LookAnd
    0.81
    whose
    0.81
     która
    0.80
    Activations Density 0.005%

    No Known Activations