© 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. 45063
    Prev
    Next
    INDEX
    Explanations

    code/technical writing

    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
     صوتيه
    -0.91
     Theſe
    -0.83
     الحره
    -0.79
     الرياضيه
    -0.79
     Normdatei
    -0.77
     raiſ
    -0.76
     ſtate
    -0.75
     Audiodateien
    -0.75
    BibitemShut
    -0.74
     purpoſe
    -0.74
    POSITIVE LOGITS
     Rosen
    0.46
     aux
    0.42
    реса
    0.41
    onaldo
    0.40
    oob
    0.40
    zuf
    0.40
    zelt
    0.40
    erez
    0.39
     pomo
    0.39
     sz
    0.39
    Activations Density 1.565%

    No Known Activations