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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 638
    Prev
    Next
    INDEX
    Explanations

    specific measurements and scientific data related to structures

    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
     or
    -0.47
     double
    -0.45
    heimer
    -0.44
    ,
    -0.42
     doble
    -0.41
    ñera
    -0.40
     
    -0.40
    double
    -0.38
    тистика
    -0.38
    muk
    -0.38
    POSITIVE LOGITS
     Efq
    0.93
    >{@
    0.89
     snippetHide
    0.87
     "..\..\..\
    0.85
    Personensuche
    0.85
    Földrajzportál
    0.82
    DockStyle
    0.80
    ⟬
    0.80
     Jefus
    0.79
    jooq
    0.76
    Activations Density 0.633%

    No Known Activations