© 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. 76468
    Prev
    Next
    INDEX
    Explanations

    October

    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
    IContainer
    -0.77
    Oct
    -0.65
     ok
    -0.58
    Ok
    -0.58
    hånd
    -0.56
    Tors
    -0.55
    oki
    -0.54
    OCT
    -0.54
    TOO
    -0.53
     Okt
    -0.53
    POSITIVE LOGITS
     ELE
    0.59
     contextLoads
    0.57
    ValueStyle
    0.56
    endphp
    0.56
    nodoc
    0.54
     Nid
    0.53
     Noodle
    0.53
    onActivityResult
    0.52
     Noo
    0.52
     Nicho
    0.51
    Activations Density 0.002%

    No Known Activations