© 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. 3521
    Prev
    Next
    INDEX
    Explanations

    instances of specific error or negative response keywords

    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
     any
    -0.95
    Datuak
    -0.89
     Any
    -0.80
     anywhere
    -0.78
     qualquer
    -0.77
     cualquier
    -0.76
     anything
    -0.76
    Any
    -0.75
    任何
    -0.75
    anything
    -0.75
    POSITIVE LOGITS
    NO
    1.67
    no
    1.47
     NO
    1.15
    NOS
    1.05
    No
    0.93
     NOS
    0.91
    noe
    0.90
    nos
    0.85
    Nos
    0.85
    noz
    0.84
    Activations Density 0.147%

    No Known Activations