© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4086
    Prev
    Next
    INDEX
    Explanations

    sudo

    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
     deſt
    -0.70
     Reſ
    -0.66
     faſt
    -0.65
     ſtre
    -0.64
     cauſe
    -0.64
     juſ
    -0.63
     myſelf
    -0.62
     ſche
    -0.61
     ſtate
    -0.61
     Theſe
    -0.61
    POSITIVE LOGITS
     >=",
    0.63
    UrlResolution
    0.56
    TestTools
    0.53
    JsonPropertyName
    0.52
     devenus
    0.51
    hoeddwyd
    0.50
    
    0.49
    NSNotification
    0.48
    paravant
    0.48
    glTex
    0.48
    Activations Density 0.023%

    No Known Activations