© 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. 6458
    Prev
    Next
    INDEX
    Explanations

    terms related to searching or requesting

    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
    mappedBy
    -0.77
     Hessian
    -0.71
    riotic
    -0.71
     Colla
    -0.68
     Compli
    -0.66
    žius
    -0.65
     everybody
    -0.64
     rime
    -0.63
     Duca
    -0.63
    öffentlich
    -0.63
    POSITIVE LOGITS
     seek
    1.43
     Seeking
    1.43
     SEEK
    1.41
     seeking
    1.38
     seeks
    1.31
     Seek
    1.31
    seeking
    1.27
     sought
    1.25
    Seek
    1.18
    Seeking
    1.16
    Activations Density 0.019%

    No Known Activations