© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43968
    Prev
    Next
    INDEX
    Explanations

    research discussions

    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
    XmlAccessType
    -0.82
    PyExc
    -0.70
     Савезне
    -0.67
    ValueStyle
    -0.66
     незавершена
    -0.65
    aduras
    -0.64
    SequentialGroup
    -0.63
     propOrder
    -0.61
     bandeau
    -0.60
     فريبيس
    -0.60
    POSITIVE LOGITS
    by
    0.78
    to
    0.66
    over
    0.66
    there
    0.65
     there
    0.64
    here
    0.59
    of
    0.57
    have
    0.56
    gy
    0.55
    gs
    0.54
    Activations Density 0.200%

    No Known Activations