© 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. 1-RES-MATRYOSHKA-DC
    7. 259
    Prev
    Next
    INDEX
    Explanations

    references to experimental results and findings

    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
    verifyException
    -0.64
     ligiloj
    -0.60
    WriteAttribute
    -0.59
     autorytatywna
    -0.59
    exitRule
    -0.59
    ResumeLayout
    -0.58
    בין
    -0.58
    RTGC
    -0.58
    ='#
    -0.57
    EndInit
    -0.57
    POSITIVE LOGITS
     results
    4.53
     Results
    4.09
     result
    4.03
    results
    3.95
    Results
    3.88
    result
    3.66
     Result
    3.59
     RESULTS
    3.56
    Result
    3.36
     résultats
    3.25
    Activations Density 0.677%

    No Known Activations