© 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. 92248
    Prev
    Next
    INDEX
    Explanations

    marriage and relationships

    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
     Мексичка
    -0.77
    protoimpl
    -0.68
    prefixer
    -0.57
    ########.
    -0.57
    mybatisplus
    -0.57
    tagHelperRunner
    -0.54
     BitmapFactory
    -0.54
    
    -0.52
    Abitanti
    -0.52
     isNameExpr
    -0.52
    POSITIVE LOGITS
    WithIOException
    0.57
     and
    0.56
    ftagPool
    0.51
     unit
    0.51
     doméstico
    0.51
    PRWEB
    0.50
     Pergamon
    0.49
    windowFixed
    0.48
     OMITTED
    0.48
    hdysval
    0.47
    Activations Density 0.000%

    No Known Activations