© 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. 11107
    Prev
    Next
    INDEX
    Explanations

    references to neural activity associated with suppression or reduction of neural responses and states indicating sobriety or bluntness

    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
    Enllaces
    -0.61
    Frid
    -0.57
     fieldNum
    -0.55
    =".
    -0.55
    JspWriter
    -0.55
    scriptcase
    -0.54
     sudad
    -0.53
     armario
    -0.52
    Ext
    -0.51
     cielos
    -0.50
    POSITIVE LOGITS
     незавершена
    0.95
    dbus
    0.82
     sober
    0.76
    leness
    0.72
    asan
    0.72
    alamus
    0.71
     blunt
    0.70
    Unmarshal
    0.69
    sev
    0.67
     nahilalakip
    0.67
    Activations Density 0.069%

    No Known Activations