© 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. 0-RES-MATRYOSHKA-DC
    7. 11823
    Prev
    Next
    INDEX
    Explanations

    expressions of fear or being afraid

    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
    cuál
    -0.52
     question
    -0.51
    NonNull
    -0.51
    PathVariable
    -0.50
    lacion
    -0.48
     peace
    -0.47
     Simplify
    -0.46
    piegel
    -0.46
    BlockPos
    -0.46
     news
    -0.45
    POSITIVE LOGITS
     afraid
    2.89
     Afraid
    2.16
    fraid
    1.88
     ashamed
    0.88
     estekak
    0.86
     otomatig
    0.78
     الحره
    0.77
    怕
    0.76
     hesitate
    0.75
     takut
    0.71
    Activations Density 0.001%

    No Known Activations