© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1320
    Prev
    Next
    INDEX
    Explanations

    temperature values, time duration values, and associated context words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    Décès
    -0.65
    ThroughAttribute
    -0.63
     year
    -0.56
    #+#
    -0.56
    year
    -0.53
     utafitiHapana
    -0.52
    ObjectModel
    -0.50
     '\\;'
    -0.50
     PLE
    -0.50
     weekly
    -0.49
    POSITIVE LOGITS
     minutes
    2.23
     minute
    2.02
     min
    1.82
    minute
    1.79
    minutes
    1.78
    min
    1.71
     mins
    1.71
     Minutes
    1.70
     minutos
    1.63
     Minute
    1.58
    Activations Density 0.556%

    No Known Activations