© 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. 43815
    Prev
    Next
    INDEX
    Explanations

    transportation and time

    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
     night
    -0.73
    :✨
    -0.69
    WebElementEntity
    -0.63
    NIGHT
    -0.58
     day
    -0.55
     of
    -0.54
     Night
    -0.53
     the
    -0.51
     dia
    -0.51
    Night
    -0.50
    POSITIVE LOGITS
    yntaxException
    0.63
    ContentAlignment
    0.62
     Roskov
    0.61
    brtc
    0.56
    ernacle
    0.55
     nahilalakip
    0.55
     SwitchCompat
    0.54
    uxxxx
    0.54
    InputBorder
    0.53
    thoscope
    0.52
    Activations Density 0.255%

    No Known Activations