© 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. 702
    Prev
    Next
    INDEX
    Explanations

    term

    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
    GraphicsUnit
    -0.80
    expandindo
    -0.70
    tvguidetime
    -0.68
     eventdata
    -0.67
     &___
    -0.66
    WithMany
    -0.65
     setEmail
    -0.63
    Appellee
    -0.62
    SourceChecksum
    -0.61
     autorytatywna
    -0.59
    POSITIVE LOGITS
     impact
    0.72
     effects
    0.66
     future
    0.59
     prospects
    0.56
     implications
    0.56
     consequences
    0.54
     outcome
    0.54
     prognosis
    0.54
     fate
    0.53
     effect
    0.52
    Activations Density 0.003%

    No Known Activations