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. 20871
    Prev
    Next
    INDEX
    Explanations

    terms related to specific types of fungi and their derivatives

    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
    InstanceState
    -0.59
    scriptcase
    -0.54
    NewUrlParser
    -0.54
    gpt
    -0.53
    #+#
    -0.52
    kirch
    -0.51
     GlobalKey
    -0.51
     getArguments
    -0.51
    (@"%@",
    -0.50
    BeginContext
    -0.49
    POSITIVE LOGITS
     betweenstory
    0.64
     Diarsipkan
    0.62
     <=",
    0.57
    født
    0.56
    XMLSchema
    0.56
    شنایی
    0.52
    hellip
    0.49
     OBITUARY
    0.49
     نسخة
    0.48
    ROIT
    0.48
    Activations Density 0.013%

    No Known Activations