© 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. 4-CLT-HP
    7. 3220
    Prev
    Next
    INDEX
    Explanations

    followed

    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
     Wikimedijinoj
    -0.70
    AndEndTag
    -0.68
     Chwiliwch
    -0.65
    WebMethod
    -0.63
    EndContext
    -0.59
    konos
    -0.57
    Tikang
    -0.55
    gwin
    -0.55
    #+#
    -0.54
     externi
    -0.54
    POSITIVE LOGITS
    <?
    0.67
    ghijklmnop
    0.64
    providedIn
    0.63
     everybody
    0.60
    ratulations
    0.58
    brainly
    0.56
     somebody
    0.54
    everybody
    0.54
     rechange
    0.54
     HomeScreen
    0.53
    Activations Density 0.002%

    No Known Activations