© 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. 15
    Prev
    Next
    INDEX
    Explanations

    technical documentation-like language, including code snippets, software names, specifications, and error messages.

    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
    enumi
    -0.48
    multirow
    -0.36
     Wayback
    -0.35
    </i>
    -0.34
    жде
    -0.33
    grav
    -0.33
     FontWeight
    -0.32
    </b>
    -0.32
    eqn
    -0.31
    onto
    -0.30
    POSITIVE LOGITS
    <bos>
    1.20
     myſelf
    0.63
     itſelf
    0.60
    ⓧ
    0.58
     Monfieur
    0.57
     kaarangay
    0.56
     whoſe
    0.56
     Efq
    0.55
     raiſ
    0.55
     themſelves
    0.54
    Activations Density 98.379%

    No Known Activations