© 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. 957
    Prev
    Next
    INDEX
    Explanations

    hexadecimal byte code values starting with 0x8

    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
     brano
    -0.68
    ícil
    -0.62
    listdir
    -0.60
    SIG
    -0.59
    HasForeignKey
    -0.57
     sembler
    -0.57
     useRouter
    -0.57
    уда
    -0.56
     PCC
    -0.56
     luy
    -0.55
    POSITIVE LOGITS
    elemField
    0.77
    曖昧さ回避
    0.63
     стаття
    0.62
    pidou
    0.60
     ResponseEntity
    0.59
    ethane
    0.59
     INI
    0.57
    HomeAsUpEnabled
    0.57
    ContentAlignment
    0.56
     Donat
    0.56
    Activations Density 0.657%

    No Known Activations