© 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. 5-CLT-HP
    7. 97842
    Prev
    Next
    INDEX
    Explanations

    code and addresses

    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
    side
    -0.48
     near
    -0.44
    Side
    -0.43
    s
    -0.42
    near
    -0.42
    bukaan
    -0.40
    ст
    -0.39
    st
    -0.38
     front
    -0.38
    ดง
    -0.38
    POSITIVE LOGITS
    parsedMessage
    0.77
    OGND
    0.77
    ContentLoaded
    0.73
    SequentialGroup
    0.73
     مشين
    0.70
     Normdatei
    0.69
    providedIn
    0.69
     referenties
    0.66
    ioutil
    0.65
     Chwiliwch
    0.65
    Activations Density 0.002%

    No Known Activations