© 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. 4-CLT-HP
    7. 4409
    Prev
    Next
    INDEX
    Explanations

    window

    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
    colgroup
    -0.60
    SBATCH
    -0.51
    łbym
    -0.49
    ément
    -0.47
    PointerException
    -0.47
    RAEL
    -0.45
    раздо
    -0.44
    indd
    -0.43
    Intermediate
    -0.42
    urbs
    -0.42
    POSITIVE LOGITS
    featureID
    0.74
    FormTagHelper
    0.71
     '\\;'
    0.69
    CURLOPT
    0.61
    iprot
    0.61
     intptr
    0.60
    GetEnumerator
    0.58
    GEBURTSDATUM
    0.57
    hearts
    0.56
    SharedCtor
    0.55
    Activations Density 0.005%

    No Known Activations