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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 10996
    Prev
    Next
    INDEX
    Explanations

    phrases related to findings and observations in research data

    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
    -1.00
    tagHelperRunner
    -0.93
     كومونز
    -0.78
    AnchorTagHelper
    -0.78
     CreateTagHelper
    -0.75
     otomatig
    -0.75
    °)
    -0.75
    RuleContext
    -0.73
    httphttps
    -0.72
     שוליים
    -0.71
    POSITIVE LOGITS
     kala
    0.48
    婿
    0.47
    TargetException
    0.46
    volution
    0.45
    splatz
    0.45
     тис
    0.45
    oluto
    0.44
     integrate
    0.44
     celo
    0.44
     africana
    0.42
    Activations Density 0.035%

    No Known Activations