© 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. 6166
    Prev
    Next
    INDEX
    Explanations

    measurements related to linear relationships in data

    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
    Abit
    -0.65
    OGEN
    -0.63
     initComponents
    -0.62
    }]);
    -0.59
    AndEndTag
    -0.58
    EnableWeb
    -0.57
     flat
    -0.54
    …]
    -0.54
    +)/
    -0.51
    Flatten
    -0.50
    POSITIVE LOGITS
     linear
    1.09
     LINEAR
    0.98
     Linear
    0.96
    Linear
    0.84
     doInBackground
    0.75
     liné
    0.72
    linear
    0.68
    ьаж
    0.67
    PhysRev
    0.66
    SequentialGroup
    0.65
    Activations Density 0.010%

    No Known Activations