© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 11019
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "for" and its variations in different 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
    }{*}{
    -0.72
    datable
    -0.63
     enfans
    -0.63
     supérieurs
    -0.61
     vectorielles
    -0.59
     reemplazo
    -0.58
    bentukan
    -0.57
     mémor
    -0.57
     bakgrund
    -0.57
     发表于
    -0.57
    POSITIVE LOGITS
    PerformLayout
    0.88
     تانيه
    0.75
    AndEndTag
    0.68
    thargy
    0.68
    OGND
    0.66
    opsida
    0.66
    TagHelper
    0.65
    րջ
    0.63
     createSlice
    0.60
    izoen
    0.59
    Activations Density 0.069%

    No Known Activations