© 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. 94268
    Prev
    Next
    INDEX
    Explanations

    ginger or crystal

    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
     Crystal
    -0.51
     Palm
    -0.48
    Crystal
    -0.48
    s
    -0.44
    Palm
    -0.40
    ANY
    -0.39
    DS
    -0.38
    appendTo
    -0.37
     state
    -0.37
    Datuak
    -0.36
    POSITIVE LOGITS
     محفوظة
    0.87
    GraphicsUnit
    0.83
     متعلقه
    0.81
    tvguidetime
    0.78
     Efq
    0.76
     مشين
    0.75
    Begriffsklä
    0.73
     виправивши
    0.72
     Wiktionnaire
    0.72
    AutoScale
    0.71
    Activations Density 1.637%

    No Known Activations