© 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. 2127
    Prev
    Next
    INDEX
    Explanations

    x

    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
    #
    -0.72
    ArgsConstructor
    -0.63
    ंदीखरीदारी
    -0.56
    <eos>
    -0.52
    Personensuche
    -0.50
    InjectAttribute
    -0.48
    protoimpl
    -0.48
    ConstraintMaker
    -0.48
     starts
    -0.47
    PathVariable
    -0.47
    POSITIVE LOGITS
     LoginComponent
    0.59
    OwnProperty
    0.57
     ""
    0.55
    riscoll
    0.54
    asional
    0.54
     esetben
    0.52
    idus
    0.52
    peted
    0.52
    efits
    0.52
    emény
    0.51
    Activations Density 0.007%

    No Known Activations