© 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. 24312
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and numerical values

    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
     BorderRadius
    -0.74
    RetentionPolicy
    -0.69
    ServletRequest
    -0.69
    ModelAdmin
    -0.68
     Exactos
    -0.66
     MediaType
    -0.66
     Trasp
    -0.65
    intenant
    -0.63
    MessageTagHelper
    -0.62
     '>=
    -0.62
    POSITIVE LOGITS
    IntoConstraints
    0.52
    mazoo
    0.42
    komsten
    0.42
    وأضاف
    0.41
    éges
    0.40
    celotti
    0.40
    来歴
    0.40
     hu
    0.40
    atosis
    0.39
    žek
    0.39
    Activations Density 0.025%

    No Known Activations