© 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. 5305
    Prev
    Next
    INDEX
    Explanations

    software use and documentation

    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
     autorytatywna
    -0.88
    +#+#
    -0.82
     متعلقه
    -0.81
     bezeichneter
    -0.79
    ensement
    -0.78
     tartalomajánló
    -0.77
     initComponents
    -0.76
    Autoritní
    -0.75
     HasFactory
    -0.73
     internetowa
    -0.73
    POSITIVE LOGITS
     effectively
    0.47
     most
    0.47
     best
    0.44
     guessed
    0.44
     hardest
    0.40
     maximise
    0.39
    urlencoded
    0.38
     MOST
    0.38
     navideño
    0.38
    best
    0.37
    Activations Density 0.000%

    No Known Activations