© 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. 5-CLT-HP
    7. 94204
    Prev
    Next
    INDEX
    Explanations

    Research data

    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
     
    -0.51
     spalle
    -0.49
    </em>
    -0.49
    </strong>
    -0.47
    2
    -0.47
    ,
    -0.47
    basicConfig
    -0.46
     K
    -0.45
    s
    -0.43
    3
    -0.43
    POSITIVE LOGITS
    expandindo
    0.93
    ंदीखरीदारी
    0.90
    دانشنامهٔ
    0.81
     myſelf
    0.79
     ſeveral
    0.78
     houſe
    0.76
     EClass
    0.75
    ^(@)
    0.73
     perſon
    0.73
    NUMX
    0.73
    Activations Density 0.010%

    No Known Activations