© 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. 0-CLT-HP
    7. 42381
    Prev
    Next
    INDEX
    Explanations

    see

    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
     can
    -0.85
     ويكيپيديا
    -0.62
    CanBe
    -0.59
     voidaan
    -0.55
     última
    -0.53
     Can
    -0.52
     cannot
    -0.52
     podemos
    -0.51
     kann
    -0.49
     last
    -0.49
    POSITIVE LOGITS
     referenties
    0.76
     houſe
    0.72
     Diſ
    0.70
     fufficient
    0.69
     preſent
    0.68
    RepeatedField
    0.68
     Kram
    0.68
     ſeveral
    0.68
     unſ
    0.67
     unpacking
    0.67
    Activations Density 0.182%

    No Known Activations