© 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. 38947
    Prev
    Next
    INDEX
    Explanations

    respectively

    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
     respectively
    -2.77
    respectively
    -2.48
     respectivamente
    -2.42
     respectivement
    -2.17
     separately
    -2.09
     respective
    -2.02
     соответственно
    -1.81
     separate
    -1.79
    separate
    -1.78
    respective
    -1.66
    POSITIVE LOGITS
     old
    0.61
     []:
    0.54
     coming
    0.52
    ắt
    0.50
    anci
    0.46
     Old
    0.45
    ,
    0.45
    !
    0.45
     الش
    0.45
     Shum
    0.45
    Activations Density 0.031%

    No Known Activations