© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5351
    Prev
    Next
    INDEX
    Explanations

    mentions of tokens related to token identification and validation

    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
    handleRequest
    -0.73
    ########.
    -0.63
    HasColumnType
    -0.62
    Personendaten
    -0.62
    DebuggerNonUser
    -0.61
    DetailComponent
    -0.60
    icons
    -0.59
     htons
    -0.58
    rawDesc
    -0.58
    Bronnen
    -0.57
    POSITIVE LOGITS
     token
    3.47
    token
    3.25
     Token
    3.02
    Token
    2.92
     tokens
    2.91
    TOKEN
    2.52
     Tokens
    2.52
     TOKEN
    2.50
    Tokens
    2.25
    tokens
    2.20
    Activations Density 0.009%

    No Known Activations