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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73936
    Prev
    Next
    INDEX
    Explanations

    Fenne

    np_max-act-logits · 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
    AutoScaleMode
    -0.76
    +#+#
    -0.72
     GenerationType
    -0.72
    RefNanny
    -0.71
     createState
    -0.71
    antigua
    -0.67
     "..\..\..\
    -0.65
     defStyleAttr
    -0.63
    AndroidJUnit
    -0.61
     Sequelize
    -0.59
    POSITIVE LOGITS
    ll
    0.51
    TagMode
    0.42
     ddelweddau
    0.41
    IMAN
    0.41
    bres
    0.41
    IPAC
    0.40
    ématiques
    0.39
    IsContent
    0.38
    bool
    0.38
    Frames
    0.37
    Activations Density 0.000%

    No Known Activations