Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 25144
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks and their usage in context

    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
    Diwedd
    -0.81
    PyExc
    -0.63
    UnsafeEnabled
    -0.62
     semej
    -0.60
    afficheront
    -0.60
    ErrUnexpectedEOF
    -0.58
    paramref
    -0.58
     Winaray
    -0.57
    BindingResult
    -0.56
    setof
    -0.56
    POSITIVE LOGITS
    classmethod
    0.56
     فريبيس
    0.53
     lexic
    0.53
     referenties
    0.52
     loaves
    0.52
     thirds
    0.51
     leaks
    0.50
     lbs
    0.50
     pounds
    0.49
     oars
    0.49
    Activations Density 0.051%

    No Known Activations