© 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. 0-RES-MATRYOSHKA-DC
    7. 11658
    Prev
    Next
    INDEX
    Explanations

    neural responses related to phospho-lipid signals, especially phospho-inositide and phospho-lipid modifications

    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
     PDE
    -0.60
     nonnegative
    -0.50
     opto
    -0.50
     Roskov
    -0.47
    กรณ์
    -0.46
     noqa
    -0.46
     aapt
    -0.45
    PDE
    -0.45
     Men
    -0.44
    parsedMessage
    -0.44
    POSITIVE LOGITS
    uminescence
    2.16
     phospho
    1.42
     Phosp
    0.86
    phospho
    0.85
    Phosp
    0.84
    RetentionPolicy
    0.73
    posedge
    0.68
     везе
    0.65
    \{\\
    0.65
     ItemStack
    0.63
    Activations Density 0.005%

    No Known Activations