© 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. 5-CLT-HP
    7. 91446
    Prev
    Next
    INDEX
    Explanations

    need want

    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
     for
    -0.46
    ,
    -0.46
    AutoScaleMode
    -0.44
     come
    -0.43
     ez
    -0.40
    ios
    -0.40
    jdt
    -0.40
    Ez
    -0.39
    PropertyGroup
    -0.39
    viti
    -0.39
    POSITIVE LOGITS
    PMailer
    0.86
    XmlAccessType
    0.77
     ſtre
    0.76
     purpoſe
    0.75
    Datuak
    0.73
    BeginContext
    0.71
     greateſt
    0.70
     pleaſure
    0.70
    setVerticalGroup
    0.69
    
    0.67
    Activations Density 0.002%

    No Known Activations