© 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. 20-CLT-HP
    7. 73641
    Prev
    Next
    INDEX
    Explanations

    programming/legal documents

    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
    -0.71
     Италијани
    -0.70
     protoimpl
    -0.68
     supérieurs
    -0.68
     nakalista
    -0.68
     Valdés
    -0.68
     мәкал
    -0.67
    出版年
    -0.66
    sidemargin
    -0.66
     kasarigan
    -0.65
    POSITIVE LOGITS
     felt
    0.63
     charged
    0.59
    felt
    0.48
     sm
    0.45
     pol
    0.45
    Felt
    0.45
     po
    0.43
     fra
    0.42
     ri
    0.42
    charged
    0.40
    Activations Density 0.000%

    No Known Activations