© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1742
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving functions and operations on variables

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.71
     calendriers
    -0.68
    EDEFAULT
    -0.66
    zzleHttp
    -0.61
    BeginContext
    -0.60
     oars
    -0.59
     vectorielle
    -0.58
     Submissions
    -0.58
     Agreg
    -0.57
    SBATCH
    -0.57
    POSITIVE LOGITS
     close
    0.51
     again
    0.50
     [
    0.50
    ↩
    0.48
    gan
    0.48
    close
    0.47
    —
    0.46
     complex
    0.45
    ==(
    0.44
     Ende
    0.44
    Activations Density 1.058%

    No Known Activations