© 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. 95137
    Prev
    Next
    INDEX
    Explanations

    in

    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
    Dis
    -0.54
    >();
    -0.54
    )]:
    -0.49
     Dis
    -0.49
    this
    -0.49
    ']))
    -0.48
    ():
    -0.47
     Th
    -0.46
     }}>
    -0.46
    Th
    -0.45
    POSITIVE LOGITS
     թվական
    0.60
     Efq
    0.60
    :✨
    0.59
    lapsingToolbar
    0.57
     InputDecoration
    0.57
    úly
    0.55
    ophone
    0.54
     Quelles
    0.53
     fevere
    0.52
    idavit
    0.52
    Activations Density 0.026%

    No Known Activations