© 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. 4-CLT-HP
    7. 3353
    Prev
    Next
    INDEX
    Explanations

    hyphens

    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
    UnknownFields
    -0.76
    simpleType
    -0.69
     CreateTagHelper
    -0.68
     time
    -0.68
    setVerticalGroup
    -0.66
    LEncoder
    -0.64
    AddTagHelper
    -0.63
     <<<<<<<<<<<<<<
    -0.63
    SharedDtor
    -0.60
     noqa
    -0.59
    POSITIVE LOGITS
     auroit
    0.65
     pouvoit
    0.54
     feroit
    0.54
     eût
    0.54
     étoit
    0.52
    //{
    0.50
     détruit
    0.49
     keberadaan
    0.47
     zoude
    0.47
     détru
    0.46
    Activations Density 0.005%

    No Known Activations