© 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. 2-RES-MATRYOSHKA-DC
    7. 5734
    Prev
    Next
    INDEX
    Explanations

    expressions of willingness or preference

    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
     said
    -1.13
    said
    -0.85
     noted
    -0.79
     explained
    -0.79
    migrationBuilder
    -0.77
     told
    -0.77
     >=",
    -0.76
     mentioned
    -0.74
     stated
    -0.74
     reported
    -0.71
    POSITIVE LOGITS
     say
    2.27
    say
    2.11
    Say
    2.08
     Say
    2.03
     SAY
    1.92
    SAY
    1.63
     Saying
    1.27
     zeggen
    1.24
     sagen
    1.22
     saying
    1.16
    Activations Density 0.063%

    No Known Activations