© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97326
    Prev
    Next
    INDEX
    Explanations

    Regret/Corrections

    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
    aris
    -0.68
    ########.
    -0.68
    #+#
    -0.66
     ErrIntOverflow
    -0.63
     وتسجيلات
    -0.59
     ImportError
    -0.58
    CloseOperation
    -0.57
    mybatisplus
    -0.56
    oneofs
    -0.56
    ufficient
    -0.55
    POSITIVE LOGITS
    s
    0.54
     دى
    0.53
     Liberties
    0.46
     dores
    0.44
     Lung
    0.43
    BrowserModule
    0.43
    ChildScrollView
    0.43
    i
    0.43
     ανά
    0.42
     Palms
    0.42
    Activations Density 1.568%

    No Known Activations