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. 8711
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting irregularities in the text

    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
    hatenablog
    -0.65
    ieteur
    -0.63
    URDAY
    -0.56
    berdayakan
    -0.55
     tarvit
    -0.55
     venons
    -0.54
     Amar
    -0.54
     undef
    -0.54
     themſelves
    -0.53
     purpoſe
    -0.53
    POSITIVE LOGITS
    findpost
    0.74
     الحره
    0.73
    writerow
    0.67
    Литература
    0.63
    OwnProperty
    0.63
    Referințe
    0.62
     kasarigan
    0.59
     ويكيميديا
    0.59
    ClassNotFound
    0.59
    (;;)
    0.59
    Activations Density 0.021%

    No Known Activations