© 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. 508
    Prev
    Next
    INDEX
    Explanations

    the word "to"

    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
    ly
    -0.62
    adays
    -0.52
    jména
    -0.48
    お
    -0.47
     gangen
    -0.46
    HideFlags
    -0.46
    theless
    -0.45
     zuständig
    -0.44
     bowiem
    -0.43
    erweise
    -0.41
    POSITIVE LOGITS
     be
    1.31
     ensure
    0.99
     avoid
    0.94
     coincide
    0.94
    plevel
    0.92
    pless
    0.91
     satisfy
    0.90
     achieve
    0.88
     illustrate
    0.88
     compensate
    0.88
    Activations Density 2.205%

    No Known Activations