© 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. 0-RES-MATRYOSHKA-DC
    7. 15559
    Prev
    Next
    INDEX
    Explanations

    references to making things up or creating false information

    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
     $_"
    -0.83
    writeFieldEnd
    -0.79
    AsUp
    -0.76
    writeField
    -0.74
    setVerticalGroup
    -0.73
     contextLoads
    -0.72
    SEGUIR
    -0.72
    InvalidProtocol
    -0.71
     auroit
    -0.71
     avoient
    -0.70
    POSITIVE LOGITS
     make
    0.60
    <bos>
    0.57
    rewsbury
    0.52
    make
    0.51
     made
    0.50
    made
    0.48
    不如
    0.46
    новниш
    0.46
     Schweiz
    0.45
    zación
    0.45
    Activations Density 0.479%

    No Known Activations