© 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. 20-CLT-HP
    7. 73494
    Prev
    Next
    INDEX
    Explanations

    Mixed, unstructured text

    np_max-act-logits · 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
     متحده
    -0.53
    исленность
    -0.51
    )^(
    -0.48
     Gautier
    -0.47
     beaches
    -0.47
    TextSpan
    -0.47
    BIS
    -0.46
     comuniques
    -0.45
     patas
    -0.44
    انيف
    -0.44
    POSITIVE LOGITS
    twimg
    0.79
    Bibliograf
    0.68
    webElementXpaths
    0.57
    Portály
    0.53
    íncipe
    0.52
    ourtney
    0.52
    pyramid
    0.51
    UnsafeEnabled
    0.51
    OGND
    0.50
    mặt
    0.50
    Activations Density 0.002%

    No Known Activations