© 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. 91925
    Prev
    Next
    INDEX
    Explanations

    things

    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
     Informal
    -0.43
     Discard
    -0.42
     uwe
    -0.42
    zension
    -0.42
    paths
    -0.42
    राब
    -0.41
    ських
    -0.40
     Coutinho
    -0.39
     manj
    -0.39
     Becomes
    -0.38
    POSITIVE LOGITS
    yntaxException
    0.90
    SequentialGroup
    0.88
     GenerationType
    0.86
    StoryboardSegue
    0.74
     AssemblyCulture
    0.72
    WriteBarrier
    0.71
     about
    0.70
    __).
    0.70
     AssemblyVersion
    0.69
    bootstrapcdn
    0.67
    Activations Density 0.102%

    No Known Activations