© 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. 3725
    Prev
    Next
    INDEX
    Explanations

    expressions of sensory perception, particularly focusing on auditory and visual features

    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
     تضيفلها
    -0.90
     itſelf
    -0.88
    antMatchers
    -0.83
    ValueStyle
    -0.82
     Egli
    -0.79
     themſelves
    -0.76
     myſelf
    -0.75
     Shakspeare
    -0.75
     uſe
    -0.73
    setVerticalGroup
    -0.71
    POSITIVE LOGITS
     &___
    0.57
    :✨
    0.51
    onia
    0.49
     g
    0.46
    __':
    0.46
     a
    0.45
     "
    0.45
     his
    0.44
     p
    0.43
    veld
    0.43
    Activations Density 0.643%

    No Known Activations