© 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. 6-RES-MATRYOSHKA-DC
    7. 1033
    Prev
    Next
    INDEX
    Explanations

    the color "red" and sometimes relates it to political topics or coloring of other things

    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
    tvguidetime
    -0.79
    RectangleBorder
    -0.74
     jScrollPane
    -0.72
    "}")
    -0.72
    KURZBESCHREIBUNG
    -0.71
     disambiguazione
    -0.68
    IsContent
    -0.66
    葩
    -0.65
    YMMV
    -0.64
    ervlak
    -0.64
    POSITIVE LOGITS
     red
    1.68
    Red
    1.66
     Red
    1.64
     RED
    1.63
    red
    1.48
    RED
    1.42
     reds
    1.41
    红
    1.28
     rosse
    1.27
     Reds
    1.25
    Activations Density 0.411%

    No Known Activations