© 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. 6584
    Prev
    Next
    INDEX
    Explanations

    claims of truth

    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
     False
    -0.73
    elemField
    -0.71
    False
    -0.70
     Nope
    -0.70
    DoubleQuotes
    -0.68
    twimg
    -0.66
    Boolean
    -0.66
     imaginary
    -0.64
     Jefus
    -0.63
    oolean
    -0.62
    POSITIVE LOGITS
     true
    1.95
    true
    1.57
     True
    1.17
     TRUE
    1.10
    True
    1.09
     verdadera
    1.04
     truest
    1.02
     verdadero
    0.98
     wahren
    0.98
     truly
    0.95
    Activations Density 0.059%

    No Known Activations