© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3183
    Prev
    Next
    INDEX
    Explanations

    ting

    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
    >(_
    -0.52
    ]")]
    -0.52
    šanai
    -0.50
    šanās
    -0.49
    encontra
    -0.49
    ējās
    -0.47
     croit
    -0.46
     Crus
    -0.45
     actief
    -0.45
    cible
    -0.44
    POSITIVE LOGITS
    וויק
    0.58
    HomeAsUpEnabled
    0.56
     BoxDecoration
    0.55
    findpost
    0.55
    KommentareTeilen
    0.54
    المناصب
    0.54
    enumii
    0.54
     timbre
    0.52
    disposing
    0.51
     Normdatei
    0.50
    Activations Density 0.008%

    No Known Activations