© 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. 2-RES-MATRYOSHKA-DC
    7. 3880
    Prev
    Next
    INDEX
    Explanations

    references to configuration files, paths, and version details related to software or system setup

    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
    D
    -0.76
     D
    -0.68
     Dik
    -0.58
     Dit
    -0.57
    󠁣
    -0.55
    DI
    -0.54
    Di
    -0.53
    Dit
    -0.53
    Dz
    -0.53
    DllImport
    -0.53
    POSITIVE LOGITS
    d
    1.40
     d
    0.93
     nakalista
    0.78
    ｄ
    0.71
     Kud
    0.68
    dge
    0.66
    dR
    0.66
    Hd
    0.63
    duled
    0.62
    dS
    0.61
    Activations Density 0.154%

    No Known Activations