© 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. 1216
    Prev
    Next
    INDEX
    Explanations

    words and phrases that refer to railways and their operation

    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
     tradução
    -0.54
     nakalista
    -0.51
     iParam
    -0.50
     ég
    -0.49
     artigian
    -0.48
    ropho
    -0.47
     artificiales
    -0.47
    htë
    -0.46
    toHave
    -0.46
     caccia
    -0.46
    POSITIVE LOGITS
     trains
    0.98
     Trains
    0.88
     train
    0.86
     locomotives
    0.84
    Trains
    0.82
     Train
    0.80
     locomotive
    0.79
     coaches
    0.78
     loco
    0.76
     locos
    0.75
    Activations Density 0.447%

    No Known Activations