© 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. 21219
    Prev
    Next
    INDEX
    Explanations

    terms related to the processes of induction and generation in scientific contexts

    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
     initComponents
    -0.99
    ſelf
    -0.91
    StoryboardSegue
    -0.90
     Paglinawan
    -0.89
    WriteBarrier
    -0.84
     itſelf
    -0.84
    thentic
    -0.81
    '},
    -0.81
    moiselle
    -0.81
    ſelves
    -0.80
    POSITIVE LOGITS
    antMatchers
    0.64
     års
    0.46
     asyncio
    0.44
     prévenir
    0.43
     deflect
    0.42
    KeyListener
    0.42
    ROUTINE
    0.42
    getFullYear
    0.42
     toutes
    0.41
     intervals
    0.41
    Activations Density 0.134%

    No Known Activations