© 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. 45228
    Prev
    Next
    INDEX
    Explanations

    succ

    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
    Atsauces
    -0.58
    tières
    -0.58
    toggler
    -0.54
    spender
    -0.51
    COE
    -0.51
    gogo
    -0.50
    coe
    -0.50
    ACTERS
    -0.50
    ی
    -0.49
    yarnpkg
    -0.49
    POSITIVE LOGITS
     Majefty
    0.88
     faſt
    0.77
     fubject
    0.77
     Jefus
    0.75
     Monfieur
    0.72
    ſelf
    0.68
     juſ
    0.67
     ſche
    0.66
     pleaſure
    0.66
     ſeveral
    0.66
    Activations Density 0.045%

    No Known Activations