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. 14623
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "set" and its variations

    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
    örté
    -0.70
    føre
    -0.56
     ExecuteAsync
    -0.56
     iesp
    -0.54
    uanya
    -0.52
     nakalista
    -0.51
     léč
    -0.51
    Véxase
    -0.50
     piemē
    -0.50
    Diweddarwch
    -0.49
    POSITIVE LOGITS
    BeginInit
    0.80
    #+#
    0.78
    +:+
    0.68
    بوابة
    0.66
    __':
    0.66
     Sist
    0.65
    __':
    
    0.65
     TextInputType
    0.65
    hant
    0.65
    __":
    
    0.65
    Activations Density 0.014%

    No Known Activations