© 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. 0-CLT-HP
    7. 94423
    Prev
    Next
    INDEX
    Explanations

    ballots

    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
    IPA
    -1.34
    cipated
    -0.88
    ipa
    -0.77
    theless
    -0.75
    espan
    -0.65
     الاطلاع
    -0.65
    ]}>
    -0.64
    %)$
    -0.63
     Paglinawan
    -0.60
    messageInfo
    -0.59
    POSITIVE LOGITS
     numberOfRows
    0.61
    gesellschaft
    0.51
    DropColumn
    0.49
     skj
    0.49
     undervis
    0.46
     offent
    0.45
     schermata
    0.45
    går
    0.45
    mybatisplus
    0.45
     bäst
    0.45
    Activations Density 0.089%

    No Known Activations