© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19306
    Prev
    Next
    INDEX
    Explanations

    occurrences of XML or HTML tags

    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
     /\.
    -1.00
    AutoScaleMode
    -0.97
    Portail
    -0.96
    তথ্যসূত্র
    -0.91
     للمعارف
    -0.90
    CloseOperation
    -0.90
     useAppContext
    -0.89
    setVerticalGroup
    -0.84
    abestanden
    -0.83
    Portale
    -0.81
    POSITIVE LOGITS
     Pres
    0.60
    te
    0.59
    1
    0.59
    ade
    0.57
     closed
    0.54
    ette
    0.53
     from
    0.52
    de
    0.51
    TE
    0.51
    e
    0.51
    Activations Density 0.013%

    No Known Activations