© 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. 2-RES-MATRYOSHKA-DC
    7. 4063
    Prev
    Next
    INDEX
    Explanations

    the stimulus parameters used for inducing long-term depression

    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
     spectra
    -0.67
    Spect
    -0.60
     spec
    -0.60
     Escri
    -0.59
    spectra
    -0.59
    spec
    -0.58
     Spect
    -0.58
    minecraftforge
    -0.56
    izing
    -0.56
    ドラ
    -0.56
    POSITIVE LOGITS
    SP
    2.67
     SP
    2.59
     SPH
    1.21
    SPP
    1.13
    sp
    1.03
     sp
    0.98
    sP
    0.94
     SSP
    0.93
    SPJ
    0.88
    SSP
    0.88
    Activations Density 0.004%

    No Known Activations