© 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. 5163
    Prev
    Next
    INDEX
    Explanations

    hist

    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
     <<<<<<<<<<<<<<
    -0.75
    يميديا
    -0.68
    })`
    -0.65
     InputDecoration
    -0.64
     ISNI
    -0.64
    例句
    -0.60
    Xna
    -0.60
    )_/¯
    -0.59
    Бахар
    -0.58
     通販
    -0.57
    POSITIVE LOGITS
    خم
    0.46
     Trans
    0.44
     ContentValues
    0.43
     ddelweddau
    0.42
    يو
    0.42
     geblieben
    0.42
    étaire
    0.42
    hlon
    0.42
    Dto
    0.42
    lick
    0.41
    Activations Density 0.015%

    No Known Activations