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. 21216
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terminology referencing measurements and specific biological or physical 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
     Grüße
    -0.63
    grunns
    -0.61
    oslav
    -0.61
    }{*}{
    -0.60
    ">:
    -0.60
    ométrie
    -0.57
    ziasztok
    -0.57
    NewUrlParser
    -0.57
     Monfieur
    -0.56
    rieks
    -0.56
    POSITIVE LOGITS
    +#+#
    0.77
    webElementXpaths
    0.59
    bootstrapcdn
    0.59
    yarnpkg
    0.52
     endwhile
    0.52
    <eos>
    0.49
     فريبيس
    0.49
    principalTable
    0.48
    iestety
    0.47
     protoimpl
    0.46
    Activations Density 0.320%

    No Known Activations