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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92917
    Prev
    Next
    INDEX
    Explanations

    almost

    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
    Przypisy
    -0.60
     voks
    -0.59
    meral
    -0.59
     وتسجيلات
    -0.59
    diez
    -0.57
     betweenstory
    -0.55
    Borrow
    -0.55
    '||
    -0.54
    Lenovo
    -0.54
    izarse
    -0.54
    POSITIVE LOGITS
    jgl
    0.51
    IndentedString
    0.50
    OnInit
    0.47
     يتيمه
    0.42
    âce
    0.41
    APORE
    0.41
    WebElementEntity
    0.41
    Encore
    0.41
     Spoilers
    0.41
     noqa
    0.40
    Activations Density 0.013%

    No Known Activations