© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4242
    Prev
    Next
    INDEX
    Explanations

    terms associated with rigidity or strictness

    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
     kasarigan
    -0.79
     Wilkins
    -0.72
    keren
    -0.72
     previa
    -0.72
     Harman
    -0.69
     Glaser
    -0.68
    </table>
    -0.67
    Liens
    -0.66
    </em>
    -0.65
    ‌ش
    -0.65
    POSITIVE LOGITS
    ded
    1.12
    sd
    0.89
     Ned
    0.88
    rid
    0.88
    gd
    0.88
     Idd
    0.85
    ddd
    0.85
    д
    0.84
     Cod
    0.84
     BUD
    0.83
    Activations Density 1.115%

    No Known Activations