© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74895
    Prev
    Next
    INDEX
    Explanations

    "B" "R" abbreviations

    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
    DockStyle
    -0.66
     PSM
    -0.60
     CMT
    -0.59
    ConstraintMaker
    -0.58
     SIA
    -0.56
     VC
    -0.55
     DMS
    -0.54
     TSM
    -0.53
     IST
    -0.52
     ISC
    -0.52
    POSITIVE LOGITS
    BR
    0.82
    BB
    0.77
    GBR
    0.76
     BR
    0.72
    Br
    0.71
    bB
    0.71
    BRI
    0.71
     BB
    0.70
    BRD
    0.69
    br
    0.68
    Activations Density 0.009%

    No Known Activations