© 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. 40672
    Prev
    Next
    INDEX
    Explanations

    remediation, regret

    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
     féminine
    -0.49
     étroite
    -0.48
    gle
    -0.48
     reap
    -0.47
    väg
    -0.47
    imdi
    -0.46
     våre
    -0.46
     før
    -0.45
    hæng
    -0.45
     remedi
    -0.43
    POSITIVE LOGITS
    ftagPool
    0.73
    ingly
    0.66
    tagHelperRunner
    0.65
     AssemblyTitle
    0.65
     initComponents
    0.64
     дописавши
    0.64
    rooms
    0.63
    sikal
    0.63
     weakly
    0.60
    Aktualisiert
    0.60
    Activations Density 1.630%

    No Known Activations