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. 14525
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics in research contexts

    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
    цездатний
    -0.83
     itſelf
    -0.80
     विश्वसनीयता
    -0.79
     tartalomajánló
    -0.78
     sumpay
    -0.78
    ]")]
    -0.76
     estekak
    -0.76
     myſelf
    -0.75
     سكانية
    -0.73
    Obrázky
    -0.69
    POSITIVE LOGITS
    帖最后由
    0.52
    الدراسه
    0.50
    禽
    0.50
     ingat
    0.49
     begy
    0.45
    hak
    0.45
    simo
    0.44
    cill
    0.43
     calo
    0.43
    insee
    0.43
    Activations Density 0.020%

    No Known Activations