© 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. 9539
    Prev
    Next
    INDEX
    Explanations

    predictions about future events or states

    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
    ReusableCell
    -0.73
    кипедия
    -0.55
    ˈ
    -0.54
    HasColumnType
    -0.50
    enumii
    -0.50
     butterknife
    -0.50
     t
    -0.49
     θ
    -0.49
     <<<<<<<<<<<<<<
    -0.49
    DockStyle
    -0.48
    POSITIVE LOGITS
    aarrggbb
    0.87
     Efq
    0.80
     Monfieur
    0.67
    TestingModule
    0.66
    frastructure
    0.65
     ſch
    0.65
     itſelf
    0.62
     SIMBAD
    0.61
     houſe
    0.61
     Theſe
    0.61
    Activations Density 0.079%

    No Known Activations