© 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. 1005
    Prev
    Next
    INDEX
    Explanations

    the prefix "anti-", sometimes also activating on "pro-"

    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
    URLException
    -0.68
     jsPsych
    -0.66
    دانشنامهٔ
    -0.65
     يتيمه
    -0.63
    ndata
    -0.59
    chtenstein
    -0.56
    titleMargin
    -0.55
    */)
    -0.55
     zad
    -0.54
     متعلقه
    -0.54
    POSITIVE LOGITS
     anti
    2.91
     Anti
    2.69
    Anti
    2.66
    anti
    2.55
     ANTI
    2.44
    ANTI
    2.20
     анти
    1.99
     antis
    1.98
    Анти
    1.95
     antic
    1.88
    Activations Density 0.117%

    No Known Activations