© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12296
    Prev
    Next
    INDEX
    Explanations

    step

    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
     step
    -0.65
     Step
    -0.64
    Step
    -0.59
    step
    -0.57
    bbene
    -0.52
     STEP
    -0.49
    STEP
    -0.47
    biases
    -0.45
     stepfather
    -0.45
     sauvages
    -0.45
    POSITIVE LOGITS
    URLException
    0.71
    CPtr
    0.65
    AttributeSet
    0.65
    InstrumentedTest
    0.61
    rungsseite
    0.60
     AssemblyCulture
    0.59
     <<<<<<<<<<<<<<
    0.58
    celotti
    0.58
    TargetException
    0.57
    AccessFile
    0.57
    Activations Density 0.325%

    No Known Activations