© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 970
    Prev
    Next
    INDEX
    Explanations

    rainwater

    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
     guild
    -0.60
    thest
    -0.56
    Ứ
    -0.56
    wiſe
    -0.55
     Chriftian
    -0.55
    alleri
    -0.54
    BSITE
    -0.54
     ſhall
    -0.53
     Jefus
    -0.53
     Moslem
    -0.53
    POSITIVE LOGITS
    JspWriter
    0.66
    ValueStyle
    0.55
     @"/
    0.54
     Exacts
    0.54
    <bos>
    0.52
    LookAnd
    0.51
    kuš
    0.50
     CURLOPT
    0.49
    tauchen
    0.47
     unknownFields
    0.47
    Activations Density 0.032%

    No Known Activations