© 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. 4994
    Prev
    Next
    INDEX
    Explanations

    otrophic

    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
    sizeCache
    -0.71
     كومونز
    -0.66
    StoreMessageInfo
    -0.64
     noires
    -0.57
     quæ
    -0.57
     rempliss
    -0.53
     Himo
    -0.52
    ItemBackground
    -0.52
     appunto
    -0.52
    Portale
    -0.52
    POSITIVE LOGITS
    tvguidetime
    0.65
    ścią
    0.56
    bootstrapcdn
    0.54
    出版年
    0.53
     ويكيپيديا
    0.53
    }")]
    0.49
    quelize
    0.49
    ngdoc
    0.49
    astify
    0.47
    homonymie
    0.47
    Activations Density 0.002%

    No Known Activations