© 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. 1-CLT-HP
    4. 642
    Prev
    Next
    INDEX
    Explanations

    diverse content formats

    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
    ंदीखरीदारी
    -0.61
    +#+#
    -0.54
    Personendaten
    -0.50
     <=",
    -0.47
    PageIndex
    -0.44
    瘠
    -0.44
    ing
    -0.44
    InitVars
    -0.42
     PK
    -0.42
     fascination
    -0.42
    POSITIVE LOGITS
     håll
    0.61
     Tenta
    0.60
    abetes
    0.58
     Winaray
    0.57
     préférence
    0.56
    śmy
    0.56
    idać
    0.55
     judiciales
    0.55
    ądź
    0.55
    ynthetic
    0.54
    Activations Density 0.000%

    No Known Activations