© 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. 4-CLT-HP
    4. 2305
    Prev
    Next
    INDEX
    Explanations

    with

    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
    oa̍t
    -0.91
     Waray
    -0.89
     schedules
    -0.80
    Hozzáférés
    -0.76
    //});
    -0.75
    writeFieldEnd
    -0.73
    ArrowToggle
    -0.73
     styles
    -0.70
     lives
    -0.70
     lifestyles
    -0.69
    POSITIVE LOGITS
     no
    0.64
     say
    0.60
     this
    0.60
     perfect
    0.55
    say
    0.52
     excellent
    0.49
     that
    0.47
     too
    0.47
     impeccable
    0.46
    ,
    0.45
    Activations Density 0.001%

    No Known Activations