© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4775
    Prev
    Next
    INDEX
    Explanations

    references to news articles or reports

    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
     Audiodateien
    -0.71
     ElementRef
    -0.68
    JNIEnv
    -0.66
    
    -0.62
    下载附件
    -0.61
    OGND
    -0.60
    Flammability
    -0.60
    MigrationBuilder
    -0.59
    WarningLevel
    -0.58
     Waray
    -0.58
    POSITIVE LOGITS
     The
    1.08
     Although
    0.93
     But
    0.92
     There
    0.92
     When
    0.92
     As
    0.91
     This
    0.89
     Since
    0.88
     While
    0.88
     Because
    0.85
    Activations Density 0.588%

    No Known Activations