© 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. 2-RES-MATRYOSHKA-DC
    7. 4261
    Prev
    Next
    INDEX
    Explanations

    references to statistical analyses

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stat
    -1.09
     Stats
    -1.08
    Stat
    -1.07
    stat
    -1.05
     stats
    -1.05
     Stat
    -1.02
    Stats
    -1.02
    stats
    -1.00
     STATS
    -0.94
    STAT
    -0.91
    POSITIVE LOGITS
    Statistical
    1.18
     Statistical
    1.18
     statistical
    0.96
    ISTICAL
    0.82
    statistical
    0.81
     nahilalakip
    0.66
    ième
    0.59
    DoubleQuotes
    0.58
    脚注の使い方
    0.58
    ​—
    0.58
    Activations Density 0.008%

    No Known Activations