© 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. 5050
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     Ab
    -0.43
     Works
    -0.40
     F
    -0.38
    Sa
    -0.38
     Fe
    -0.37
    ↵↵
    -0.36
     Are
    -0.36
     T
    -0.36
     E
    -0.36
     Es
    -0.35
    POSITIVE LOGITS
    WriteTagHelper
    0.99
     виправивши
    0.88
    ########.
    0.82
    stdafx
    0.78
    ^(@)
    0.77
     doubtnut
    0.77
     hObject
    0.77
     $_"
    0.77
    hematical
    0.75
    μως
    0.75
    Activations Density 0.021%

    No Known Activations