© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3146
    Prev
    Next
    INDEX
    Explanations

    S

    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
    <bos>
    -0.45
    zeczytaj
    -0.36
    APIView
    -0.34
    ExecuteReader
    -0.34
     NPs
    -0.33
     trajectories
    -0.32
     respondents
    -0.31
     obvious
    -0.31
     turkey
    -0.31
    其实
    -0.30
    POSITIVE LOGITS
    tvguidetime
    0.81
    expandindo
    0.79
    MigrationBuilder
    0.76
    DIPSETTING
    0.71
     يتيمه
    0.66
     gynhyrchwyd
    0.65
    TagMode
    0.64
    FromArgb
    0.63
     محفوظة
    0.61
    oporosis
    0.60
    Activations Density 0.005%

    No Known Activations