© 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. 20-CLT-HP
    7. 73613
    Prev
    Next
    INDEX
    Explanations

    August

    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
     Signalez
    -0.75
    tagHelperRunner
    -0.60
    AndEndTag
    -0.58
     iNdEx
    -0.57
    EndGlobalSection
    -0.57
    ніципалі
    -0.57
    igert
    -0.56
     PagesJaunes
    -0.56
    UnknownFieldSet
    -0.56
    UnusedPrivate
    -0.55
    POSITIVE LOGITS
    thinkable
    0.44
    ThroughAttribute
    0.44
    MUX
    0.43
    tamol
    0.41
    monių
    0.39
     møte
    0.37
    Hozzáférés
    0.36
     VIAF
    0.36
    crollView
    0.35
     фо
    0.35
    Activations Density 0.001%

    No Known Activations