© 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. 96115
    Prev
    Next
    INDEX
    Explanations

    course

    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
     صوتيه
    -0.75
    DockStyle
    -0.75
    abetes
    -0.69
     gynhyrchwyd
    -0.69
    riction
    -0.58
    Diweddarwch
    -0.54
     RIPRODUZIONE
    -0.51
     pinulongan
    -0.51
     tand
    -0.50
    RenderAtEndOf
    -0.50
    POSITIVE LOGITS
    +#+
    0.60
     Familienname
    0.48
     JR
    0.47
    Begriffsklä
    0.46
    InstrumentedTest
    0.46
    횟
    0.43
    存于互联网档案馆
    0.43
    sizeCache
    0.43
     committee
    0.42
    endpush
    0.42
    Activations Density 0.000%

    No Known Activations