© 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. 2651
    Prev
    Next
    INDEX
    Explanations

    statements indicating that something is considered interesting or noteworthy

    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
    issauga
    -0.67
     ajuns
    -0.64
     preuves
    -0.62
     thoracic
    -0.61
     normalidad
    -0.60
     superiore
    -0.60
     tă
    -0.60
    superior
    -0.59
     flesta
    -0.59
     mengucap
    -0.59
    POSITIVE LOGITS
     interesting
    1.21
     interests
    1.19
     Interesting
    1.18
    interesting
    1.17
     interest
    1.13
     intress
    1.13
    Interesting
    1.12
     INTEREST
    1.12
     interess
    1.09
    Interess
    1.08
    Activations Density 0.037%

    No Known Activations