© 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. 1020
    Prev
    Next
    INDEX
    Explanations

    instances of "for" followed by a number and the letter "h", likely representing experimental durations in hours

    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
     tartalomajánló
    -1.04
     decade
    -1.03
     year
    -0.99
     AssemblyVersion
    -0.89
    year
    -0.89
     years
    -0.88
     década
    -0.82
     Year
    -0.81
     YEAR
    -0.81
    years
    -0.81
    POSITIVE LOGITS
     hours
    1.48
     Hours
    1.29
    hours
    1.20
     hour
    1.20
    Hours
    1.18
    hour
    1.16
     horas
    1.15
     Hour
    1.15
     HOURS
    1.13
    Hour
    1.10
    Activations Density 0.446%

    No Known Activations