© 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. 5-CLT-HP
    7. 93502
    Prev
    Next
    INDEX
    Explanations

    Technology and locations

    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
     nakalista
    -0.57
    કા
    -0.56
    zeln
    -0.56
     المعيارى
    -0.53
    abela
    -0.53
    LabelTagHelper
    -0.51
     espir
    -0.50
    stdc
    -0.50
    everywhere
    -0.50
    SourceChecksum
    -0.49
    POSITIVE LOGITS
     including
    0.62
    حياته
    0.56
     due
    0.53
    ########.
    0.52
     excluding
    0.52
     كومونز
    0.51
     however
    0.50
    bjs
    0.50
    PreExecute
    0.49
    Jeografia
    0.49
    Activations Density 0.003%

    No Known Activations