© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11544
    Prev
    Next
    INDEX
    Explanations

    concrete

    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
    avedra
    -0.63
     aikaa
    -0.54
    berdayakan
    -0.54
    savevideobot
    -0.53
    saucony
    -0.53
    entrums
    -0.53
    RTLE
    -0.52
    tshell
    -0.51
     citoy
    -0.51
     Rtl
    -0.51
    POSITIVE LOGITS
     يتيمه
    0.63
    SourceChecksum
    0.55
    addCriterion
    0.53
    orous
    0.50
    autique
    0.50
    unque
    0.49
    oneofs
    0.46
    arm
    0.46
     بتاريخ
    0.45
     soit
    0.45
    Activations Density 0.086%

    No Known Activations