© 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. 1002
    Prev
    Next
    INDEX
    Explanations

    angle bracket code, code-related terms, technical terms, names, other languages, or words with "hat" or "ing" in them

    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
     DriverManager
    -0.88
    lobo
    -0.77
     MonoBehaviour
    -0.73
     Rij
    -0.72
    ccf
    -0.70
     Corcoran
    -0.69
    //
    -0.68
     Pembroke
    -0.68
    Hochspringen
    -0.68
    IANGLES
    -0.68
    POSITIVE LOGITS
    hat
    0.93
    bate
    0.93
     Pate
    0.92
     ATE
    0.92
     Hat
    0.89
     rat
    0.88
     Rat
    0.88
    atoon
    0.88
    Frat
    0.87
     Slat
    0.87
    Activations Density 2.218%

    No Known Activations