© 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. 5661
    Prev
    Next
    INDEX
    Explanations

    negative values or sentiments

    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
    Répondre
    -0.57
     ITIS
    -0.54
    více
    -0.54
    ¿½
    -0.51
     Обе
    -0.50
    drv
    -0.49
    ForKey
    -0.48
    GNA
    -0.47
    ẫ
    -0.47
     BorderLayout
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.91
     للاسماء
    0.77
     nakalista
    0.76
    makeConstraints
    0.73
    Viited
    0.73
    expandindo
    0.73
    AutoScaleMode
    0.72
    AccessorTable
    0.71
    gdx
    0.69
    verwijspagina
    0.69
    Activations Density 0.010%

    No Known Activations