© 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. 26045
    Prev
    Next
    INDEX
    Explanations

    statements and questions related to mathematical or logical expressions and their evaluations

    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
    <sup>
    -0.40
     usual
    -0.38
    mrow
    -0.38
    <sub>
    -0.36
      
    -0.35
    まして
    -0.34
     nes
    -0.34
    lá
    -0.34
     “
    -0.33
    gesellschaft
    -0.33
    POSITIVE LOGITS
    UnusedPrivate
    0.89
    الإنجليزية
    0.85
    WebElementEntity
    0.85
     kaarangay
    0.84
    rawDesc
    0.84
    цездатний
    0.84
    ########.
    0.83
     Administrativna
    0.83
    KommentareTeilen
    0.83
     oprot
    0.82
    Activations Density 0.497%

    No Known Activations