© 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. 19198
    Prev
    Next
    INDEX
    Explanations

    references to living spaces or areas within a home

    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
    #
    -0.48
    EndInit
    -0.47
    差
    -0.47
     quota
    -0.46
     Klo
    -0.46
     Privat
    -0.46
    utet
    -0.46
     Foul
    -0.46
    ha
    -0.45
     Micro
    -0.44
    POSITIVE LOGITS
     Wohnzimmer
    0.84
     myſelf
    0.73
    客厅
    0.71
     becauſe
    0.69
     itſelf
    0.69
     Theſe
    0.66
    andidaten
    0.65
     Livingston
    0.65
    ArgumentParser
    0.64
     themſelves
    0.63
    Activations Density 0.006%

    No Known Activations