© 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. 6-RES-MATRYOSHKA-DC
    7. 739
    Prev
    Next
    INDEX
    Explanations

    legal citations

    oai_token-act-pair · gemini-2.0-flash
    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
     Monfieur
    -0.99
     itſelf
    -0.98
     myſelf
    -0.96
     ―――――
    -0.84
     ExecuteAsync
    -0.84
     Anſ
    -0.83
     Reſ
    -0.83
    parsedMessage
    -0.82
     themſelves
    -0.80
    LookAnd
    -0.79
    POSITIVE LOGITS
    ⓧ
    0.52
     
    0.50
    di
    0.47
    SA
    0.46
    xmlns
    0.46
    Collegamenti
    0.45
     frutta
    0.45
    dig
    0.44
    ham
    0.44
    fas
    0.44
    Activations Density 0.323%

    No Known Activations