© 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. 25248
    Prev
    Next
    INDEX
    Explanations

    instructions related to keyboard inputs and key presses

    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
    ostom
    -0.55
    haustible
    -0.53
     кли
    -0.51
    Default
    -0.51
    munk
    -0.50
     clip
    -0.49
    wind
    -0.49
    PreferredItem
    -0.48
     explore
    -0.48
    qü
    -0.48
    POSITIVE LOGITS
    GEBURTSDATUM
    0.84
    ConstraintMaker
    0.69
    contentLoaded
    0.64
    ########.
    0.64
    EndContext
    0.64
     tibial
    0.63
    Попис
    0.62
    HostException
    0.61
    évaluateur
    0.60
     transfieras
    0.58
    Activations Density 0.014%

    No Known Activations