© 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. 3283
    Prev
    Next
    INDEX
    Explanations

    statements about the unaffected status or impossibility of a condition or event

    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
     bad
    -0.75
     Bad
    -0.71
     UN
    -0.67
    ANDUM
    -0.67
     terrible
    -0.66
     Un
    -0.65
    Bad
    -0.65
    OGND
    -0.64
     menge
    -0.63
    UN
    -0.61
    POSITIVE LOGITS
     unable
    1.19
     impossible
    1.14
    impossible
    1.09
     impossibility
    1.07
     unaffected
    1.06
     unavailable
    1.04
     ineligible
    1.03
     unreachable
    1.02
     Unable
    1.00
     inaccessible
    0.99
    Activations Density 0.187%

    No Known Activations