© 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. 2038
    Prev
    Next
    INDEX
    Explanations

    Miz

    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
    ISupport
    -0.75
     nakalista
    -0.67
    rupulous
    -0.63
     purpoſe
    -0.62
    Portale
    -0.62
     doubtnut
    -0.61
     ſeveral
    -0.60
    Населення
    -0.60
    Демографія
    -0.60
    DockStyle
    -0.59
    POSITIVE LOGITS
    ScopeManager
    0.50
    rungsseite
    0.49
    oram
    0.46
    omar
    0.40
    orm
    0.39
    sieme
    0.39
     lam
    0.39
     Lom
    0.39
    orno
    0.37
    ork
    0.37
    Activations Density 0.001%

    No Known Activations