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. 11427
    Prev
    Next
    INDEX
    Explanations

    references to text file formats

    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
    ല
    -0.79
    pel
    -0.74
    Pel
    -0.73
    ച
    -0.73
    रे
    -0.73
     επ
    -0.65
    chin
    -0.64
    Ef
    -0.64
    ('=
    -0.64
     Pel
    -0.64
    POSITIVE LOGITS
     txt
    1.16
    txt
    1.07
    rungsseite
    1.02
     Txt
    0.93
    Txt
    0.89
    HandlerContext
    0.84
     الحره
    0.82
    [--
    0.82
     sumpay
    0.81
    +][
    0.81
    Activations Density 0.006%

    No Known Activations