© 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. 22-RES-MATRYOSHKA-DC
    7. 1945
    Prev
    Next
    INDEX
    Explanations

    phrases containing 'the', prepositions and words with negative connotations such as 'below', 'falls'

    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
     esternos
    -0.51
    xtures
    -0.50
    abestanden
    -0.50
    genheit
    -0.50
     nahilalakip
    -0.50
     cherchés
    -0.49
    srcs
    -0.49
     الرياضيه
    -0.48
    ilarities
    -0.48
    RenderAtEndOf
    -0.47
    POSITIVE LOGITS
     threshold
    1.75
     limit
    1.63
     limits
    1.50
     thresholds
    1.49
    threshold
    1.39
     limite
    1.33
     seuil
    1.30
     limites
    1.27
    limit
    1.26
     Threshold
    1.24
    Activations Density 2.321%

    No Known Activations