© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77294
    Prev
    Next
    INDEX
    Explanations

    Formal language and proper nouns

    np_max-act-logits · 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
    $.
    -0.19
    Re
    -0.18
    Ch
    -0.18
    Co
    -0.18
    Ar
    -0.18
    PG
    -0.18
    AP
    -0.17
    Cu
    -0.17
    St
    -0.17
    </strong>
    -0.17
    POSITIVE LOGITS
     Efq
    1.50
    ^(@)
    1.49
     myſelf
    1.41
     doubtnut
    1.36
     itſelf
    1.36
     Majefty
    1.34
     themſelves
    1.33
     himſelf
    1.30
     $_"
    1.30
     Jefus
    1.26
    Activations Density 0.000%

    No Known Activations