© 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. 1-CLT-HP
    7. 10718
    Prev
    Next
    INDEX
    Explanations

    Chamber

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chamber
    -1.06
    Chamber
    -1.03
     CHAMBER
    -1.00
     chamber
    -0.88
     condemned
    -0.81
     Condem
    -0.78
     Chamberlain
    -0.77
     Chambers
    -0.77
     chambers
    -0.77
    chamber
    -0.74
    POSITIVE LOGITS
     Extragalactic
    0.50
     überweisen
    0.46
    rigkeit
    0.42
    น์
    0.40
    TokenNameEQUAL
    0.40
    әр
    0.40
    bigcap
    0.39
    Brothers
    0.39
     russe
    0.39
     Brothers
    0.39
    Activations Density 0.037%

    No Known Activations