© 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. 24247
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or expressions equal to a specified value

    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
    BeginContext
    -0.71
    itinéraire
    -0.68
    StoryboardSegue
    -0.65
    MigrationBuilder
    -0.63
     cruzado
    -0.61
    Referències
    -0.60
     kasarigan
    -0.59
    GEBURTSDATUM
    -0.59
     متعلقه
    -0.58
    jgl
    -0.56
    POSITIVE LOGITS
    TabIndex
    0.54
    boh
    0.52
    ']));
    0.49
     Op
    0.48
    vares
    0.47
    一出
    0.46
    ட்ச
    0.45
    acchi
    0.45
     adven
    0.44
     fa
    0.44
    Activations Density 0.035%

    No Known Activations