© 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. 20154
    Prev
    Next
    INDEX
    Explanations

    references to temperature

    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
     kasarigan
    -1.09
     فريبيس
    -0.94
     reaſon
    -0.90
     itſelf
    -0.90
     uſe
    -0.89
     themſelves
    -0.87
     Theſe
    -0.87
     purpoſe
    -0.86
     uſed
    -0.86
     pleaſure
    -0.86
    POSITIVE LOGITS
    y
    0.81
    e
    0.77
     Charlie
    0.73
    Charlie
    0.67
     Lang
    0.66
     &
    0.65
    um
    0.65
     McIntyre
    0.63
    AssignableFrom
    0.63
    tem
    0.62
    Activations Density 0.017%

    No Known Activations