© 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. 2822
    Prev
    Next
    INDEX
    Explanations

    statements expressing an inability or impossibility

    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
     оригіналу
    -0.82
    ształ
    -0.65
     not
    -0.63
    mallow
    -0.61
     ujednoznacz
    -0.60
     OMITBAD
    -0.60
    chymal
    -0.60
    phemy
    -0.60
    ="@+
    -0.59
    AnchorStyles
    -0.58
    POSITIVE LOGITS
     cannot
    2.14
    cannot
    2.06
     Cannot
    2.05
    Cannot
    1.91
     CANNOT
    1.73
     cant
    1.42
    Cant
    1.31
     CANT
    1.30
     Cant
    1.28
     unable
    1.22
    Activations Density 0.064%

    No Known Activations