© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43709
    Prev
    Next
    INDEX
    Explanations

    fieldName

    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
    encers
    -1.95
    pery
    -0.58
    rungsseite
    -0.57
    zeß
    -0.53
     الحره
    -0.49
    jarse
    -0.49
     speciale
    -0.48
     ordinaires
    -0.47
     teilnehmen
    -0.47
    OCCURRED
    -0.47
    POSITIVE LOGITS
     Koll
    0.65
    Clik
    0.55
     Mutual
    0.55
     saar
    0.53
    DoubleQuotes
    0.53
    flashdata
    0.52
    sqcup
    0.52
     Gue
    0.51
     brou
    0.51
    cplusplus
    0.51
    Activations Density 1.597%

    No Known Activations