© 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. 0-CLT-HP
    7. 42821
    Prev
    Next
    INDEX
    Explanations

    clear

    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
     clear
    -2.03
    clear
    -1.49
     Clear
    -1.48
    Clear
    -1.34
     CLEAR
    -1.10
     clearer
    -1.05
     clearness
    -0.94
     clearest
    -0.93
    CLEAR
    -0.93
     klare
    -0.90
    POSITIVE LOGITS
    -
    0.69
    ball
    0.60
    headed
    0.60
    cut
    0.59
    Palmar
    0.59
    MigrationBuilder
    0.58
    bones
    0.57
    bare
    0.57
    brain
    0.57
     ngũ
    0.56
    Activations Density 0.022%

    No Known Activations