© 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
    2. Gemma-2-2B
    3. 18-RES-MATRYOSHKA-DC
    4. 100
    Prev
    Next
    INDEX
    Explanations

    words related to problem-solving, solutions, and justifications

    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
    <bos>
    -1.15
     Мексичка
    -1.12
    ',
    
    
    -1.08
    '},
    
    -1.06
    `,
    
    -1.06
    '],
    
    -1.04
    '),
    
    -0.93
    (),
    
    -0.93
    Архівовано
    -0.92
    "},
    
    -0.92
    POSITIVE LOGITS
    .
    1.77
    ↵↵
    1.18
    。
    1.05
    ).
    1.03
    <eos>
    0.98
    ."
    0.96
    .”
    0.93
    ।
    0.93
    ↵↵↵
    0.90
    !
    0.89
    Activations Density 20.590%

    No Known Activations