© 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. 77869
    Prev
    Next
    INDEX
    Explanations

    Wish

    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
    complexContent
    -0.78
     للمعارف
    -0.76
    OGND
    -0.70
     jury
    -0.67
     TextAppearance
    -0.66
     AssemblyProduct
    -0.66
    BeginContext
    -0.65
    EditorBrowsable
    -0.63
    RuleContext
    -0.60
    SequentialGroup
    -0.59
    POSITIVE LOGITS
    heids
    0.47
    ORR
    0.45
    LPG
    0.43
    lipp
    0.40
    BSP
    0.39
     préfère
    0.39
    SBATCH
    0.38
    lė
    0.38
    })));
    0.38
    í
    0.38
    Activations Density 0.000%

    No Known Activations