© 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. 0-CLT-HP
    7. 1842
    Prev
    Next
    INDEX
    Explanations

    it

    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
     is
    -0.62
    معلومات
    -0.56
     Normdatei
    -0.55
    ValueStyle
    -0.53
    <bos>
    -0.51
     beträgt
    -0.51
    uxxxx
    -0.51
     falls
    -0.50
     does
    -0.49
     verg
    -0.48
    POSITIVE LOGITS
     imply
    0.82
     are
    0.82
     happen
    0.82
     contain
    0.79
     continue
    0.79
     refer
    0.75
     apply
    0.75
     reflect
    0.73
     depend
    0.73
     were
    0.72
    Activations Density 0.152%

    No Known Activations