© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25496
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing conditional reasoning or premises in logical arguments

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     sauter
    -0.62
    __["
    -0.53
    \#\#
    -0.52
    ?)
    -0.52
    enumi
    -0.52
     since
    -0.50
     previous
    -0.50
    haria
    -0.50
    มาย
    -0.49
    ho
    -0.49
    POSITIVE LOGITS
    ynchronously
    0.82
    CloseOperation
    0.68
    Erreferentziak
    0.67
    gdx
    0.67
     Tacitus
    0.66
     cellulite
    0.64
     Moderator
    0.63
     Eros
    0.63
     moderator
    0.62
    AndPassword
    0.61
    Activations Density 0.011%

    No Known Activations