© 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. 792
    Prev
    Next
    INDEX
    Explanations

    code snippets with a combination of the words "to", "trying", "want," "would", "try", " without" ,"could" and "should"

    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
     pinulongan
    -0.59
     please
    -0.55
     file
    -0.55
     Please
    -0.49
     i
    -0.47
     which
    -0.47
    abestanden
    -0.47
     using
    -0.46
     with
    -0.45
     object
    -0.45
    POSITIVE LOGITS
     Normdatei
    0.69
    ^(@)
    0.68
    Viitteet
    0.66
    קישורים
    0.65
    Lähteet
    0.64
     inför
    0.63
    AddRef
    0.63
     disambiguazione
    0.60
    ✨:
    0.60
     blest
    0.57
    Activations Density 0.722%

    No Known Activations