© 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. 5-CLT-HP
    7. 4679
    Prev
    Next
    INDEX
    Explanations

    unseen

    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
    новниш
    -0.74
     Infórmanos
    -0.67
     defaultstate
    -0.67
    UnknownFieldSet
    -0.65
     Winaray
    -0.63
     Computational
    -0.63
     impossibility
    -0.62
     '\\;'
    -0.62
    ارنة
    -0.61
    findpost
    -0.61
    POSITIVE LOGITS
    ,
    0.54
     from
    0.47
    ModelAttribute
    0.45
     hati
    0.44
    NgModule
    0.44
    .
    0.44
    __(/*!
    0.44
    formKey
    0.43
    ::*;
    0.42
    IndentedString
    0.41
    Activations Density 0.002%

    No Known Activations