© 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. 0-RES-MATRYOSHKA-DC
    7. 14345
    Prev
    Next
    INDEX
    Explanations

    the emphasis on "telling" and related communication actions

    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
    FieldBuilder
    -0.75
    bitField
    -0.71
    LookAnd
    -0.69
     ISNI
    -0.67
    خصة
    -0.65
    RunWith
    -0.65
    Personensuche
    -0.63
    BufferException
    -0.63
     تضيفلها
    -0.62
    الحياه
    -0.60
    POSITIVE LOGITS
     telling
    1.98
     Telling
    1.45
    Telling
    1.30
    telling
    1.26
     storytelling
    0.77
     narration
    0.68
     Storytelling
    0.61
    enderror
    0.57
    Story
    0.57
    story
    0.56
    Activations Density 0.002%

    No Known Activations