© 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. 4719
    Prev
    Next
    INDEX
    Explanations

    question marks

    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
    elstein
    -0.49
     me
    -0.47
     the
    -0.47
     on
    -0.46
     and
    -0.46
     fact
    -0.45
     so
    -0.44
     an
    -0.44
     no
    -0.44
    hede
    -0.44
    POSITIVE LOGITS
    XmlAccessType
    0.92
    providedIn
    0.86
    NameInMap
    0.85
    +#+#
    0.84
    Then
    0.81
    UnknownFieldSet
    0.80
     photolibrary
    0.77
    tagHelperRunner
    0.77
     pleaſure
    0.76
    then
    0.75
    Activations Density 0.004%

    No Known Activations