© 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. 0-CLT-HP
    7. 38978
    Prev
    Next
    INDEX
    Explanations

    LT

    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
    :✨
    -0.78
     newOwner
    -0.70
    ]")]
    -0.70
     "..\..\
    -0.65
    principalColumn
    -0.65
    ✨:
    -0.63
     հղումներ
    -0.63
    קישורים
    -0.63
    enapa
    -0.60
    WithIOException
    -0.60
    POSITIVE LOGITS
    U
    0.58
    amp
    0.54
    TA
    0.54
    P
    0.54
    K
    0.54
    PA
    0.53
    Ber
    0.53
    Z
    0.53
    ’
    0.52
    F
    0.52
    Activations Density 0.071%

    No Known Activations