Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3839
    Prev
    Next
    INDEX
    Explanations

    a

    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
     "..\..\
    -0.73
    »-
    -0.68
    ”-
    -0.66
     '-':
    -0.66
     kaarangay
    -0.65
    "):
    -0.65
     "..\..\..\
    -0.65
    ”—
    -0.64
    ]=-
    -0.64
     '+':
    -0.63
    POSITIVE LOGITS
    .
    0.94
     IBOutlet
    0.56
     avoient
    0.49
    mybatisplus
    0.48
     valutazione
    0.48
    prnewswire
    0.48
    astify
    0.47
     piattaforma
    0.47
     refusé
    0.46
     enfans
    0.46
    Activations Density 0.008%

    No Known Activations