© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 303
    Prev
    Next
    INDEX
    Explanations

    segments of code

    oai_token-act-pair · gemini-2.0-flash
    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
    ")==
    -0.65
    )|^{
    -0.57
    )<\
    -0.55
     morreu
    -0.54
     Bres
    -0.53
     McGovern
    -0.52
     Dore
    -0.52
    ulman
    -0.50
    versiti
    -0.50
    anganronpa
    -0.50
    POSITIVE LOGITS
    self
    1.80
     self
    1.51
    Self
    1.41
     Self
    1.39
     SELF
    1.34
    SELF
    1.23
     selves
    1.08
    weakSelf
    0.94
    __':
    0.83
     nonatomic
    0.82
    Activations Density 0.863%

    No Known Activations