© 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. 6602
    Prev
    Next
    INDEX
    Explanations

    expressions of personal knowledge or awareness

    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
     unknown
    -1.10
    Known
    -1.05
     Known
    -1.05
    known
    -1.00
     KNOWN
    -1.00
     known
    -0.94
    unknown
    -0.94
     Unknown
    -0.93
    Unknown
    -0.91
     UNKNOWN
    -0.91
    POSITIVE LOGITS
     know
    1.60
    know
    1.21
     Know
    1.15
    Know
    1.11
     knows
    1.09
     KNOW
    1.04
    KNOW
    0.94
    knows
    0.79
     wissen
    0.72
    知道
    0.64
    Activations Density 0.101%

    No Known Activations