© 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. 5-CLT-HP
    7. 1120
    Prev
    Next
    INDEX
    Explanations

    Software and user interaction

    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
    Хьажоргаш
    -0.84
    <bos>
    -0.69
     chi̍t
    -0.68
     Мексичка
    -0.66
     myſelf
    -0.65
     itſelf
    -0.63
     yourselves
    -0.63
     yourself
    -0.62
    ſelves
    -0.60
     Ketch
    -0.58
    POSITIVE LOGITS
    fromnode
    0.53
     zvuky
    0.46
    XtraEditors
    0.45
     envíos
    0.42
     हमें
    0.42
    __':
    0.42
     menggambarkan
    0.41
    كونات
    0.40
    hidupan
    0.40
     kehadiran
    0.39
    Activations Density 0.010%

    No Known Activations