© 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. 91163
    Prev
    Next
    INDEX
    Explanations

    EV and robo

    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
    EV
    -0.62
     EV
    -0.61
    fu
    -0.52
    RetentionPolicy
    -0.49
    ref
    -0.47
    ScopeManager
    -0.46
    useState
    -0.45
    ギー
    -0.43
     in
    -0.43
    يميديا
    -0.42
    POSITIVE LOGITS
     Monfieur
    0.68
     NUKAT
    0.68
     fubject
    0.67
     myſelf
    0.66
     commerciales
    0.60
     poffible
    0.59
     Sarm
    0.59
    labus
    0.59
    ilson
    0.59
    liato
    0.58
    Activations Density 0.105%

    No Known Activations