© 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. 5-CLT-HP
    7. 94824
    Prev
    Next
    INDEX
    Explanations

    aim, goal, objective

    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
     Cutter
    -0.47
    >>()
    -0.45
    omal
    -0.43
    BEGIN
    -0.42
     NSCoder
    -0.41
    qid
    -0.41
    äum
    -0.40
    bezpe
    -0.40
    changers
    -0.40
    Bindable
    -0.39
    POSITIVE LOGITS
     defaultstate
    0.86
     was
    0.85
    styleType
    0.76
     pinulongan
    0.75
    IsContent
    0.74
    WebVitals
    0.70
    UnusedPrivate
    0.66
    Rujuakan
    0.64
     were
    0.63
    SourceChecksum
    0.63
    Activations Density 0.012%

    No Known Activations