© 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. 18-RES-MATRYOSHKA-DC
    7. 284
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers related to statistical data

    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.18.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.18.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
    HostException
    -0.46
    ])));
    -0.45
    ABN
    -0.43
     Thousands
    -0.40
    mio
    -0.39
    ":"",
    -0.39
    )=>{
    -0.39
    ServiceModel
    -0.39
    \_
    -0.39
    љу
    -0.39
    POSITIVE LOGITS
     percentage
    1.53
     percent
    1.50
     (%)
    1.41
     Percentage
    1.40
     Percent
    1.39
    percent
    1.38
    percentage
    1.37
     percentages
    1.36
     PERCENT
    1.35
    (%)
    1.27
    Activations Density 1.506%

    No Known Activations