© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13870
    Prev
    Next
    INDEX
    Explanations

    references to the process of removing or ejecting something, specifically related to ejection actions

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    createCanvas
    -0.51
    nastics
    -0.50
    enumii
    -0.49
     forgotten
    -0.48
     kalem
    -0.48
    shots
    -0.48
     calldata
    -0.47
    الله
    -0.47
    AutoScaleMode
    -0.47
     shadowed
    -0.47
    POSITIVE LOGITS
     ejection
    3.36
     ejected
    2.88
     eject
    2.72
     expuls
    1.04
     expulsion
    0.88
     expelled
    0.85
     expel
    0.82
     egress
    0.72
    jection
    0.69
     مشين
    0.69
    Activations Density 0.001%

    No Known Activations