© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30172
    Prev
    Next
    INDEX
    Explanations

    instances of the word "first."

    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
     calendriers
    -0.79
    ệm
    -0.70
     tartalomajánló
    -0.66
    yntaxException
    -0.65
    ucksack
    -0.64
     AssemblyCompany
    -0.63
    Extinguishing
    -0.62
    Identyfik
    -0.62
     Jard
    -0.61
     للاسماء
    -0.60
    POSITIVE LOGITS
     Insel
    0.57
    
    0.56
    uillez
    0.56
    orenje
    0.54
     schö
    0.53
    clearfix
    0.52
    脚注の使い方
    0.51
    󠁮
    0.51
    wait
    0.51
    szönöm
    0.49
    Activations Density 0.014%

    No Known Activations