© 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. 1057
    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
    oa̍t
    -0.63
     jsPsych
    -0.53
    TagHelper
    -0.52
    Geografía
    -0.52
    MENAFN
    -0.50
     OnInit
    -0.50
    most
    -0.50
    
    -0.50
     nô
    -0.49
    numerusform
    -0.49
    POSITIVE LOGITS
    ptonshire
    0.54
    windowFixed
    0.54
    itchfield
    0.54
    issauga
    0.52
     noqa
    0.50
    allets
    0.46
    unhofer
    0.46
    marginHorizontal
    0.46
     Вікіпе
    0.45
     onOptions
    0.45
    Activations Density 0.001%

    No Known Activations