© 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. 4-CLT-HP
    7. 1045
    Prev
    Next
    INDEX
    Explanations

    image fragments

    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
    Uninitialized
    -0.56
    Abit
    -0.56
    isation
    -0.50
    ymce
    -0.50
    saraba
    -0.50
    ()?;
    -0.48
    EClass
    -0.47
    حياته
    -0.46
     sichtbar
    -0.46
    uku
    -0.45
    POSITIVE LOGITS
     Roskov
    0.70
     виправивши
    0.60
     onData
    0.59
     bParam
    0.59
    IActionResult
    0.56
    rants
    0.54
    SerializeField
    0.53
    Ārējās
    0.53
     otomatig
    0.52
    HasAnnotation
    0.52
    Activations Density 0.009%

    No Known Activations