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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 3585
    Prev
    Next
    INDEX
    Explanations

    code characters

    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
     Lake
    -0.48
     West
    -0.47
     Rest
    -0.46
     Av
    -0.45
     East
    -0.44
     V
    -0.44
     process
    -0.44
     Down
    -0.43
     sand
    -0.43
     And
    -0.43
    POSITIVE LOGITS
    numerusform
    0.60
    StructEnd
    0.57
     Waray
    0.53
     mijne
    0.52
     zijne
    0.52
    vereign
    0.51
    (@"%@",
    0.50
    didReceive
    0.50
    getFrom
    0.50
    ();)
    0.50
    Activations Density 0.049%

    No Known Activations