© 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. 4-CLT-HP
    7. 48
    Prev
    Next
    INDEX
    Explanations

    follow

    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
    出版年
    -1.02
    RTEE
    -0.70
    Portale
    -0.69
    UnusedPrivate
    -0.68
    DockStyle
    -0.67
     transfieras
    -0.66
    Kanpo
    -0.65
     Drain
    -0.65
    acchar
    -0.62
    rijfs
    -0.62
    POSITIVE LOGITS
    adpleegd
    0.47
    arq
    0.38
    ائی
    0.35
    Composable
    0.35
     sabotage
    0.35
     indietro
    0.35
    ówek
    0.34
    softc
    0.34
    ByDefault
    0.33
     atún
    0.33
    Activations Density 0.002%

    No Known Activations