© 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. 4-CLT-HP
    7. 4372
    Prev
    Next
    INDEX
    Explanations

    .

    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
     crossorigin
    -0.64
    ]-->
    -0.56
    BeginInit
    -0.53
    batore
    -0.50
    izr
    -0.47
    ImageContext
    -0.47
    ）』
    -0.46
     ""],
    -0.46
     المعيارى
    -0.46
    ucchini
    -0.45
    POSITIVE LOGITS
    MigrationBuilder
    0.51
    ñales
    0.50
    ureusement
    0.49
    styleType
    0.49
     '\\;'
    0.49
    nloa
    0.48
    istoitu
    0.48
    ähte
    0.47
     transfieras
    0.46
     nakalista
    0.45
    Activations Density 0.004%

    No Known Activations