© 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. 4378
    Prev
    Next
    INDEX
    Explanations

    z

    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
     exc
    -0.47
    initas
    -0.46
     zvuky
    -0.44
     WIR
    -0.43
     externi
    -0.43
     Приступљено
    -0.43
    inx
    -0.43
    landi
    -0.42
    AutoScaleMode
    -0.42
    chomp
    -0.41
    POSITIVE LOGITS
     derog
    0.57
     ArrayAdapter
    0.55
     صوتيه
    0.53
     (;;)
    0.52
     Lessing
    0.51
    Espèce
    0.50
    greSQL
    0.50
     Graz
    0.50
    eseorang
    0.50
     isotropic
    0.50
    Activations Density 0.001%

    No Known Activations