© 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. 20-CLT-HP
    7. 76887
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act-logits · 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
    rungsseite
    -0.72
    ]--;
    -0.62
    entuh
    -0.62
    IUrlHelper
    -0.60
    __(/*!
    -0.59
    !*\
    -0.59
     reproach
    -0.58
     WebDriverWait
    -0.57
    migrationBuilder
    -0.56
     ExecuteAsync
    -0.55
    POSITIVE LOGITS
    principalColumn
    0.68
     Dra
    0.60
    Dra
    0.56
    dra
    0.53
     ti
    0.52
     Tien
    0.51
     Ti
    0.50
     dra
    0.49
     Bau
    0.49
     Maurer
    0.48
    Activations Density 0.000%

    No Known Activations