© 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. 24-RES-MATRYOSHKA-DC
    7. 15
    Prev
    Next
    INDEX
    Explanations

    clauses starting with prepositions

    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.24.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.24.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
    ^(@)
    -0.85
     étoit
    -0.78
     enfans
    -0.71
     säll
    -0.69
     démocr
    -0.69
     remporté
    -0.69
     содержи
    -0.68
     besök
    -0.67
     introducido
    -0.67
     vinto
    -0.66
    POSITIVE LOGITS
     making
    1.67
     putting
    1.51
     taking
    1.49
     doing
    1.41
     giving
    1.41
     getting
    1.38
     creating
    1.36
     bringing
    1.31
     trying
    1.27
     having
    1.27
    Activations Density 7.339%

    No Known Activations