© 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. 3-RES-MATRYOSHKA-DC
    7. 3058
    Prev
    Next
    INDEX
    Explanations

    mentions of costs or payments

    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
     itſelf
    -0.68
    XXXXXXXX
    -0.64
    Vander
    -0.63
    iade
    -0.63
     Houſe
    -0.61
    Xf
    -0.61
     }}$}
    -0.60
    mitives
    -0.59
     Prest
    -0.59
    eterminate
    -0.58
    POSITIVE LOGITS
     fee
    3.13
     Fee
    3.00
     fees
    2.92
     Fees
    2.86
     FEE
    2.67
    Fee
    2.63
    Fees
    2.58
    fee
    2.55
    fees
    2.47
     FEES
    2.45
    Activations Density 0.007%

    No Known Activations