© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24769
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "jump" and its variations, indicating a focus on actions or transitions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    ">—
    -0.66
    RectF
    -0.61
    Filmografie
    -0.60
     ketat
    -0.60
     Roh
    -0.60
     rédaction
    -0.60
     rahasia
    -0.59
     asunto
    -0.58
     فإن
    -0.57
    ]_
    -0.57
    POSITIVE LOGITS
     Jump
    1.65
     JUMP
    1.63
     jump
    1.61
     jumps
    1.61
    Jump
    1.55
    jump
    1.55
     Leap
    1.54
     leap
    1.45
     Jumping
    1.45
    Jumping
    1.45
    Activations Density 0.037%

    No Known Activations