© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2561
    Prev
    Next
    INDEX
    Explanations

    in

    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
    सन्दर्भ
    -0.71
     sanoo
    -0.57
     madura
    -0.57
     massima
    -0.55
     liitty
    -0.55
     osallist
    -0.55
    odils
    -0.53
     rencont
    -0.53
    anz
    -0.52
    ürd
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    0.60
     يتيمه
    0.59
    #+#
    0.57
    SequentialGroup
    0.53
    tagHelperRunner
    0.53
     AppCompatTheme
    0.51
     defaultstate
    0.51
    AddTagHelper
    0.51
    WebElementEntity
    0.48
    )))));
    0.47
    Activations Density 0.001%

    No Known Activations