© 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. 1123
    Prev
    Next
    INDEX
    Explanations

    Names and company names

    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
     itſelf
    -1.33
     Theſe
    -1.30
     Diſ
    -1.22
     Efq
    -1.21
     Anſ
    -1.20
     themſelves
    -1.19
     ―――――
    -1.18
     Reſ
    -1.16
     Monfieur
    -1.16
     Jefus
    -1.15
    POSITIVE LOGITS
    s
    0.57
    g
    0.45
    c
    0.45
    r
    0.44
    ra
    0.44
    rasse
    0.41
    removeAttr
    0.40
     capo
    0.40
    sg
    0.39
    m
    0.39
    Activations Density 0.121%

    No Known Activations