© 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. 17838
    Prev
    Next
    INDEX
    Explanations

    terms related to occurrences or frequencies of events

    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
    cientes
    -0.79
     Jaffe
    -0.79
     embora
    -0.79
     صوتيه
    -0.75
     vastaan
    -0.75
    $\$$
    -0.73
    amico
    -0.72
     xxvi
    -0.71
    θεν
    -0.71
    =',
    -0.70
    POSITIVE LOGITS
     MotionEvent
    0.84
     NSCoder
    0.80
     occur
    0.78
     ocorrer
    0.75
    +#+#
    0.75
     occurs
    0.75
     recor
    0.74
    occur
    0.74
    exécution
    0.73
     Occur
    0.73
    Activations Density 0.040%

    No Known Activations