© 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. 32561
    Prev
    Next
    INDEX
    Explanations

    specific temporal markers or phrases indicating time

    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
     Roskov
    -0.78
     Partagez
    -0.72
    JoinColumn
    -0.71
     NACIONAL
    -0.70
     onPostExecute
    -0.70
    ästi
    -0.68
     referenties
    -0.68
     héro
    -0.65
    antMatchers
    -0.65
     kvinder
    -0.64
    POSITIVE LOGITS
     صوتيه
    0.63
     mer
    0.59
    Encyclopædia
    0.55
    Datuak
    0.54
     cir
    0.54
     MER
    0.53
     ram
    0.51
     Mer
    0.51
    入る
    0.51
    walde
    0.51
    Activations Density 0.041%

    No Known Activations