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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 26152
    Prev
    Next
    INDEX
    Explanations

    closing punctuation in various contexts, particularly in scientific writing or references

    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
    lapsible
    -0.82
    Архівовано
    -0.75
    anonym
    -0.74
    solete
    -0.72
     Stol
    -0.69
    rieu
    -0.69
    estars
    -0.68
     AssemblyCompany
    -0.67
    cerely
    -0.67
    sial
    -0.67
    POSITIVE LOGITS
    "})
    0.76
    ("")]
    0.64
     Utica
    0.63
    Билгалдахарш
    0.63
     vendar
    0.62
     Karang
    0.61
    KommentareTeilen
    0.60
     pinulongan
    0.60
    Logan
    0.60
     Eastwood
    0.59
    Activations Density 0.009%

    No Known Activations