© 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. 91996
    Prev
    Next
    INDEX
    Explanations

    Requests/Suggestions/Reluctance

    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
    Portale
    -0.59
     EdgeInsets
    -0.47
    RegressionTest
    -0.43
    lwjgl
    -0.43
    golang
    -0.43
     дово
    -0.43
     UIApplication
    -0.40
    moveToFirst
    -0.40
    SequentialGroup
    -0.40
    ibatis
    -0.39
    POSITIVE LOGITS
    сылкі
    0.59
    
    0.56
     pinning
    0.56
    ξεις
    0.54
    новременно
    0.54
     saites
    0.54
    rungsseite
    0.53
     pinned
    0.53
     Wake
    0.52
    ริง
    0.52
    Activations Density 0.003%

    No Known Activations