© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2195
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    rungsseite
    -0.73
     disambiguazione
    -0.69
    $_['
    -0.67
    Chham
    -0.67
    webElementXpaths
    -0.65
     getF
    -0.61
     vPvB
    -0.60
    AddHtmlAttribute
    -0.59
     endblock
    -0.57
    Lähteet
    -0.56
    POSITIVE LOGITS
    éndolo
    0.47
     gangen
    0.44
    éndole
    0.43
    bayan
    0.43
    loài
    0.43
    Controllo
    0.42
    Aka
    0.42
    ]();
    0.42
     scn
    0.41
    ayant
    0.40
    Activations Density 0.002%

    No Known Activations