© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10839
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to transcription processes

    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
    :✨
    -0.81
     فريبيس
    -0.73
    ientôt
    -0.72
     Exacts
    -0.66
    orteur
    -0.66
    __*/
    -0.65
    FailureListener
    -0.65
     payee
    -0.63
    وفاته
    -0.62
    adze
    -0.62
    POSITIVE LOGITS
     itſelf
    0.66
     traves
    0.65
     varargin
    0.60
    "]).
    0.60
    GHIJKLM
    0.59
     myſelf
    0.57
     Lovel
    0.57
    ăț
    0.55
     controver
    0.54
    stdc
    0.54
    Activations Density 0.039%

    No Known Activations