© 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. 20-CLT-HP
    7. 73414
    Prev
    Next
    INDEX
    Explanations

    ,\

    np_max-act-logits · 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
    umoj
    -0.59
     ANCHE
    -0.54
    nodoc
    -0.54
     cjs
    -0.53
     архивлан
    -0.52
     catch
    -0.51
    SPJ
    -0.50
    楔
    -0.50
    sief
    -0.50
     Licht
    -0.49
    POSITIVE LOGITS
     '\\;'
    0.73
    SequentialGroup
    0.66
    RTEX
    0.61
     évêque
    0.56
    Portale
    0.55
    Sucesor
    0.52
     Figura
    0.52
     MediaQuery
    0.50
     gynhyrchwyd
    0.50
     giuri
    0.47
    Activations Density 0.000%

    No Known Activations