© 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. 4687
    Prev
    Next
    INDEX
    Explanations

    Carter

    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
    Personensuche
    -0.70
     nakalista
    -0.58
     BoxDecoration
    -0.57
    yelitis
    -0.54
    ]")]
    -0.54
     الحره
    -0.54
    findpost
    -0.52
    "]').
    -0.51
    mueble
    -0.51
    锈钢
    -0.51
    POSITIVE LOGITS
     فريبيس
    0.56
     useParams
    0.56
     times
    0.52
    ureusement
    0.51
     wondered
    0.50
     Times
    0.50
     يتيمه
    0.50
     until
    0.50
     TIMES
    0.49
    aarrggbb
    0.49
    Activations Density 0.013%

    No Known Activations