© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 721
    Prev
    Next
    INDEX
    Explanations

    the word "not", and anything adjacent to it

    oai_token-act-pair · gemini-2.0-flash
    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
    Keine
    -0.73
    Kein
    -0.71
    NotBe
    -0.69
     no
    -0.66
     seraient
    -0.63
    No
    -0.63
     No
    -0.59
    Kann
    -0.57
     Kein
    -0.57
     pourront
    -0.57
    POSITIVE LOGITS
    httphttps
    1.05
    URLException
    0.95
    yntaxException
    0.90
     يتيمه
    0.89
    +#+#
    0.88
    )')
    0.87
     Egli
    0.86
    ViewFeatures
    0.82
    >")
    0.81
    piram
    0.81
    Activations Density 0.195%

    No Known Activations