© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92781
    Prev
    Next
    INDEX
    Explanations

    rain

    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
    ISupport
    -0.52
    domada
    -0.50
     PropTypes
    -0.49
     /\.(
    -0.48
    Datuak
    -0.48
     /\.
    -0.47
     SwitchCompat
    -0.47
    klärung
    -0.47
    thera
    -0.46
    FontOfSize
    -0.46
    POSITIVE LOGITS
     magasiner
    0.54
    AndEndTag
    0.52
    ExecuteReader
    0.50
     Waray
    0.50
     dripping
    0.48
    ureusement
    0.48
     Roskov
    0.47
    wash
    0.46
     swelled
    0.46
     washed
    0.45
    Activations Density 0.001%

    No Known Activations