© 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. 738
    Prev
    Next
    INDEX
    Explanations

    patterns involving the variable 'f', particularly focusing on its numerical value or derivatives

    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
     F
    -0.92
    F
    -0.75
     Fa
    -0.58
     Ф
    -0.57
     Fow
    -0.55
    นวน
    -0.53
     Fer
    -0.52
    Fp
    -0.50
     Fo
    -0.49
     Fio
    -0.49
    POSITIVE LOGITS
    f
    2.08
     f
    1.66
    fR
    1.08
    fD
    1.05
     ƒ
    1.03
    fP
    1.02
    𝑓
    0.96
    ƒ
    0.94
    fA
    0.87
    fag
    0.87
    Activations Density 0.321%

    No Known Activations