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. 25864
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to limits and products

    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
    كتشاف
    -0.65
     HasFactory
    -0.64
     storici
    -0.64
    TRIBUTION
    -0.62
    InitVars
    -0.61
    WithIOException
    -0.59
    +#+#
    -0.57
    fromnode
    -0.57
     للاسماء
    -0.56
    getMenuInflater
    -0.55
    POSITIVE LOGITS
     ministries
    0.49
     miteinander
    0.47
    recent
    0.44
     affidavits
    0.44
    bkz
    0.43
     bun
    0.42
    flu
    0.42
     aapt
    0.42
    发表于
    0.41
    arch
    0.41
    Activations Density 0.158%

    No Known Activations