© 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. 4-CLT-HP
    7. 1657
    Prev
    Next
    INDEX
    Explanations

    report

    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
    they
    -0.64
     समीक्षक
    -0.63
    الإنجليزية
    -0.60
     հղումներ
    -0.59
     THEY
    -0.56
    THEY
    -0.56
     varandra
    -0.56
    They
    -0.55
     they
    -0.55
    by
    -0.53
    POSITIVE LOGITS
     our
    0.68
     preliminary
    0.64
    oneofs
    0.60
     IVA
    0.59
     findings
    0.58
    BeginContext
    0.57
    utives
    0.57
    "])
    0.56
     ourselves
    0.56
     BoxDecoration
    0.55
    Activations Density 0.029%

    No Known Activations