© 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. 1-RES-MATRYOSHKA-DC
    7. 345
    Prev
    Next
    INDEX
    Explanations

    references to specific phase values, particularly phase 9

    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
    ATOM
    -0.49
    soort
    -0.47
    NameInMap
    -0.47
     Тру
    -0.46
     atom
    -0.45
    牲
    -0.45
    先
    -0.45
    itsch
    -0.44
    udin
    -0.43
    spender
    -0.43
    POSITIVE LOGITS
     phase
    5.00
    phase
    4.63
     Phase
    4.53
    Phase
    4.44
     PHASE
    4.31
     phases
    4.22
    PHASE
    4.03
     Phases
    3.77
    phases
    3.59
    Phases
    3.31
    Activations Density 0.069%

    No Known Activations