© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92480
    Prev
    Next
    INDEX
    Explanations

    endor

    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
    willReturn
    -0.66
    a
    -0.63
    y
    -0.58
    Tikang
    -0.55
    es
    -0.54
    ی
    -0.54
    thenReturn
    -0.53
    Personensuche
    -0.52
    ;->
    -0.51
    fjspx
    -0.48
    POSITIVE LOGITS
     ligiloj
    0.78
    Aiheesta
    0.65
    PerformLayout
    0.64
    \}_{
    0.60
    tvguidetime
    0.60
    mappedBy
    0.58
    indd
    0.57
     समीक्षाओं
    0.57
     GenerationType
    0.56
    űr
    0.55
    Activations Density 0.053%

    No Known Activations