© 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. 935
    Prev
    Next
    INDEX
    Explanations

    forum/guide text

    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
    jkl
    -0.65
     Comp
    -0.63
     comp
    -0.55
    tech
    -0.55
     Nor
    -0.54
     tech
    -0.53
     nor
    -0.53
    Comp
    -0.53
     Tech
    -0.52
     can
    -0.49
    POSITIVE LOGITS
    Geplaatst
    0.68
    ngdoc
    0.67
     Normdatei
    0.67
    HideFlags
    0.66
    tanleria
    0.66
    writeFieldEnd
    0.65
    WebMethod
    0.65
    WebVitals
    0.63
     Majefty
    0.63
     ejus
    0.63
    Activations Density 0.023%

    No Known Activations