© 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. 77216
    Prev
    Next
    INDEX
    Explanations

    various contexts

    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
    XmlAccessType
    -0.66
     enabled
    -0.56
     Enabled
    -0.54
    ulipas
    -0.53
    IBarButtonItem
    -0.49
    rigues
    -0.49
     Италијани
    -0.49
    เอง
    -0.48
    ENIX
    -0.48
     Serra
    -0.48
    POSITIVE LOGITS
    __((
    0.62
     nakalista
    0.48
    AddTagHelper
    0.48
     NgModule
    0.48
    +#+
    0.48
    ᅠ
    0.48
     STRESS
    0.47
    RegressionTest
    0.45
    ]})
    0.45
     stress
    0.45
    Activations Density 0.000%

    No Known Activations