© 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. 3267
    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
     الحره
    -0.79
     >=",
    -0.66
    +#+
    -0.65
     متعلقه
    -0.65
    WritableDatabase
    -0.62
    __(/*!
    -0.61
     arşivlendi
    -0.59
    SequentialGroup
    -0.59
    XmlAccessType
    -0.59
     utafitiHapana
    -0.58
    POSITIVE LOGITS
    奈川
    0.52
    IBOutlet
    0.51
     mouseClicked
    0.45
     geldig
    0.45
     gun
    0.43
    XtraGrid
    0.42
    ῦ
    0.40
    ("$.
    0.38
    gebra
    0.38
    στά
    0.38
    Activations Density 0.002%

    No Known Activations