© 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. 0-CLT-HP
    7. 41970
    Prev
    Next
    INDEX
    Explanations

    trif

    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
     Reſ
    -0.94
     Anſ
    -0.81
     Efq
    -0.80
     pleaſure
    -0.78
     ſtre
    -0.76
     Majefty
    -0.76
     ſeveral
    -0.75
     Diſ
    -0.74
     Jefus
    -0.74
     ſche
    -0.74
    POSITIVE LOGITS
    Filmografie
    0.59
    ]}>
    0.57
     Ba
    0.56
    Linki
    0.56
    InstanceState
    0.52
    ponses
    0.52
     GetEnumerator
    0.52
    unar
    0.50
    ogar
    0.49
    êcher
    0.48
    Activations Density 0.150%

    No Known Activations